- Dynamic neural networks (DNNs) can adapt to varying resource availability on edge devices through techniques like incremental training and group convolution pruning. This allows meeting requirements for timing, power/energy, and accuracy.
- Experiments on two embedded platforms showed that dynamic DNNs combined with DVFS and task mapping can reduce energy consumption while maintaining classification accuracy compared to static DNNs.
- Runtime power management is needed to coordinate heterogeneous processors, respond to environmental factors, balance power consumption and battery life, and meet requirements for concurrently executing tasks and applications under varying conditions on edge devices.
Next IIoT wave: embedded digital twin for manufacturing IRS srl
Next IIoT wave will be a population of digital twin. A digital twin is a real-time digital replica of a physical device. Developing an embedded digital twin allows superior device diagnostic and failure anticipation. Discover how to to implement an embedded digital twin using real-time monitoring, physical models, and machine learning
I gave this talk at the 'Digital Twin Conference' hosted by LH Corp at COEX, Seoul on August 8th, 2019.
Abstract: 'Digital Twin' is a digital replication of real world objects, processes, phenomena that can be used for various purposes. Digital twin concept backs to manufacturing industry in early 2000s for the PLM (Product Lifecycle Management) purposes. It is based on the idea that a digital informational construct about a physical system could be created as an entity on its own. Definitions of digital twin emphasize the three important levels or characteristics. At first, there should be connection between real physical world and corresponding virtual world. To do this, Level 1 digital twin provides virtual 3D models. Secondly, this connection between real world and virtual world is established by generating (near) real time data using sensors or IoT. This is called Level 2 digital twin. Thirdly, Level 3 digital twin carries out certain analyses, predictions, and simulations using virtual 3D and (near) real time data. ‘Smart Spaces’ are interactive environments where humans and technology can openly communicate with each other in a physical or digital setting. Examples of smart spaces include smart cities, smart factories, and smart homes. ‘Smart Spaces’ is one of Garner’s Top 10 Tech Trends for 2019. As spaces are going through digital transformation with 4th industrial revolution, there are many attempts to apply digital twin technology to manage urban, spatial, and industrial issues around the world. Those attempts look set to play an increasingly important role in the creation of smart cities, smart factories, and smart homes. Bringing the virtual and real worlds together in this way can help to give better analysis, visualization, and simulation to the decision-making process. This will be a multi-way process with iterative feedback among stakeholders.
In this talk, I'll share my real experiences in carrying out digital twin and smart space projects. Also I’ll talk about what I’ve learnt from these projects.
I. Metaverse Enterprise Platform
Metaverse Enterprise Platform
Metaverse Enterprise Platform System Components
Metaverse Enterprise Use Case - AI Innovation Platform
Metaverse Enterprise Use Case - Digital Twin Retail Store
Metaverse Enterprise Use Case - Global Supply Chain Risk Mitigation
Metaverse Enterprise Use Case – Energy Management Optimization
Immersive 3D Digital Twin Platform Demo
II. ESG Digital Transformation for Profitably Sustainable Business
ESG Sustainability Imperative
How ESGDX Can Create New Revenue Streams?
ESG + Digital Transformation (ESGDX) Business Model
Digital Decarbonization
Climate Risk & Net-Zero Management Automation
Digital Twins for Dynamic Carbon Net-Zero Management
Digital Twins Use Case: A Pulp/Paper Company in S. Korea
Digital Twins for Building Net-Zero Management
Climate Risk & Net-Zero Management Digital Twins Under Development
Industrial/Enterprise Metaverse Forum & ESG DX Forum
III. Digital Twins Design & Development
Digital Twin Types
Digital Twin Models
Digital Twins + IoT + Big Data Analytics + AI
Wind Turbine Metaverse Digital Twin Design & Development
Driving Computer Vision Research Innovation In Artificial IntelligenceNVIDIA
Get a recap of the news out of NVIDIA's announcements at CVPR 2017 with highlights such as our V100 giveaway to top researchers, technical demos, workshops, and more.
A digital twin is a virtual representation of a physical object that can be used to help optimize business decisions. The webinar discusses the history and definition of digital twins, how they are enabled by technologies like IoT, and how companies are using them. Digital twins allow a physical object and its virtual counterpart to be connected, providing a closed loop between the simulated and physical worlds to improve conceptualization, comparison, and remote collaboration.
Harness the Power of AI and Deep Learning for BusinessNVIDIA
Jim McHugh, NVIDIA VP and GM of Data Center, discussed how GPU computing has accelerated artificial intelligence and deep learning capabilities. GPU computing performance has increased by 1000x by 2025, growing at 1.5x per year, compared to single-threaded microprocessor performance which has grown at only 1.1x per year. GPU computing now powers major advances in artificial intelligence, driving improvements in customer service, machine learning, data visualization, and open source collaboration.
Next IIoT wave: embedded digital twin for manufacturing IRS srl
Next IIoT wave will be a population of digital twin. A digital twin is a real-time digital replica of a physical device. Developing an embedded digital twin allows superior device diagnostic and failure anticipation. Discover how to to implement an embedded digital twin using real-time monitoring, physical models, and machine learning
I gave this talk at the 'Digital Twin Conference' hosted by LH Corp at COEX, Seoul on August 8th, 2019.
Abstract: 'Digital Twin' is a digital replication of real world objects, processes, phenomena that can be used for various purposes. Digital twin concept backs to manufacturing industry in early 2000s for the PLM (Product Lifecycle Management) purposes. It is based on the idea that a digital informational construct about a physical system could be created as an entity on its own. Definitions of digital twin emphasize the three important levels or characteristics. At first, there should be connection between real physical world and corresponding virtual world. To do this, Level 1 digital twin provides virtual 3D models. Secondly, this connection between real world and virtual world is established by generating (near) real time data using sensors or IoT. This is called Level 2 digital twin. Thirdly, Level 3 digital twin carries out certain analyses, predictions, and simulations using virtual 3D and (near) real time data. ‘Smart Spaces’ are interactive environments where humans and technology can openly communicate with each other in a physical or digital setting. Examples of smart spaces include smart cities, smart factories, and smart homes. ‘Smart Spaces’ is one of Garner’s Top 10 Tech Trends for 2019. As spaces are going through digital transformation with 4th industrial revolution, there are many attempts to apply digital twin technology to manage urban, spatial, and industrial issues around the world. Those attempts look set to play an increasingly important role in the creation of smart cities, smart factories, and smart homes. Bringing the virtual and real worlds together in this way can help to give better analysis, visualization, and simulation to the decision-making process. This will be a multi-way process with iterative feedback among stakeholders.
In this talk, I'll share my real experiences in carrying out digital twin and smart space projects. Also I’ll talk about what I’ve learnt from these projects.
I. Metaverse Enterprise Platform
Metaverse Enterprise Platform
Metaverse Enterprise Platform System Components
Metaverse Enterprise Use Case - AI Innovation Platform
Metaverse Enterprise Use Case - Digital Twin Retail Store
Metaverse Enterprise Use Case - Global Supply Chain Risk Mitigation
Metaverse Enterprise Use Case – Energy Management Optimization
Immersive 3D Digital Twin Platform Demo
II. ESG Digital Transformation for Profitably Sustainable Business
ESG Sustainability Imperative
How ESGDX Can Create New Revenue Streams?
ESG + Digital Transformation (ESGDX) Business Model
Digital Decarbonization
Climate Risk & Net-Zero Management Automation
Digital Twins for Dynamic Carbon Net-Zero Management
Digital Twins Use Case: A Pulp/Paper Company in S. Korea
Digital Twins for Building Net-Zero Management
Climate Risk & Net-Zero Management Digital Twins Under Development
Industrial/Enterprise Metaverse Forum & ESG DX Forum
III. Digital Twins Design & Development
Digital Twin Types
Digital Twin Models
Digital Twins + IoT + Big Data Analytics + AI
Wind Turbine Metaverse Digital Twin Design & Development
Driving Computer Vision Research Innovation In Artificial IntelligenceNVIDIA
Get a recap of the news out of NVIDIA's announcements at CVPR 2017 with highlights such as our V100 giveaway to top researchers, technical demos, workshops, and more.
A digital twin is a virtual representation of a physical object that can be used to help optimize business decisions. The webinar discusses the history and definition of digital twins, how they are enabled by technologies like IoT, and how companies are using them. Digital twins allow a physical object and its virtual counterpart to be connected, providing a closed loop between the simulated and physical worlds to improve conceptualization, comparison, and remote collaboration.
Harness the Power of AI and Deep Learning for BusinessNVIDIA
Jim McHugh, NVIDIA VP and GM of Data Center, discussed how GPU computing has accelerated artificial intelligence and deep learning capabilities. GPU computing performance has increased by 1000x by 2025, growing at 1.5x per year, compared to single-threaded microprocessor performance which has grown at only 1.1x per year. GPU computing now powers major advances in artificial intelligence, driving improvements in customer service, machine learning, data visualization, and open source collaboration.
Digital twins are precise virtual representations of physical objects that use collected data from sensors to display information. They consist of a physical object, its virtual twin, and the data connection between them. By 2021, half of large industrial companies are expected to use digital twins, improving effectiveness by 10%. Digital twins have various applications and allow real-time updates, data analysis, and product optimization. However, they require constant sensor data, large datasets, and internet connectivity to achieve full accuracy.
Digital Twin at-a-glance, Yong @SEMIforteYong Wang
Digital twins are virtual representations of physical objects or systems which are expected to proliferate greatly by 2020. They allow real-time data from sensors to be integrated into virtual models to enable optimization and self-monitoring. For manufacturing, digital twins of products, factories and performance can be created using data from design, building and operations to enable benefits like smart scheduling, preventative maintenance and maximized output. The semiconductor industry is well-positioned to benefit from digital twins as it already collects extensive operational data and has the computing power required.
NVIDIA Testimony at Senate Commerce, Science, and Transportation Committee He...NVIDIA
Rob Csongor, VP and General Manager of NVIDIA's automotive business, provides his testimony on the important subject of self-driving vehicle technology.
Fueling the Next Wave of AI Discovery - CVPR 2018NVIDIA
The CVPR annual conference showcases the most important advances in computer vision, pattern recognition, machine learning and artificial intelligence. Catch up on the top 5 announcements that came out of CVPR 2018.
The Best of AI and HPC in Healthcare and Life SciencesNVIDIA
Trends. Success stories. Training. Networking.
The GPU Technology Conference brings this all to one place. Meet the people pioneering the future of healthcare and life sciences and learn how to apply the latest AI and HPC tools to your research.
The AI Opportunity in Federal - Key Highlights from GTC DC 2018NVIDIA
Every industry will be empowered by AI from autonomous vehicles and robotics to healthcare and agriculture. The computational power that AI can provide will streamline workflows, maximize efficiencies, and open doors to new discoveries.
The document discusses preparing organizations for digital twins using IoT platforms and technologies like AI, analytics, and cloud services. It emphasizes positioning AI to augment human insights, reinventing operations with new digital data sources, and leveraging proven industrial expertise. Digital twins can provide real-time virtual representations of physical systems to improve decision making across their lifecycles using multiple data sources and models. The document recommends preparing for digital twins as part of an extensible IoT platform.
This document discusses advances in deep learning and AI through partnerships between NVIDIA and top research institutions. It summarizes that NVIDIA delivered its DGX-1 AI supercomputer to UC Berkeley and Mass General Hospital to accelerate breakthroughs in deep learning for tasks like analyzing medical data and autonomous vehicles. Applications highlighted include isolating speech from noise, predicting health risks from genes, and allowing NVIDIA to test self-driving vehicles in California.
A digital twin is a digital replica of a living or non-living physical entity. By bridging the physical and the virtual world, data is transmitted seamlessly allowing the virtual entity to exist simultaneously with the physical entity.
See: El Saddik, A. (2018). Digital Twins: The Convergence of Multimedia Technologies. IEEE MultiMedia, 25(2), 87-92.
This seminar report discusses digital twins, which create living digital simulation models of physical assets. A digital twin continuously learns and updates itself from multiple real-time data sources to represent the current status of its corresponding physical twin. The report provides definitions of different types of digital twins and discusses how GE uses digital twins for applications like asset management, operations optimization, and advanced controls. It also covers the characteristics and advantages of digital twins, as well as examples of their use in various industrial sectors.
Digital twins: the power of a virtual visual copy - Unite Copenhagen 2019Unity Technologies
From buildings and infrastructure to industrial machinery and factories, digital twins are becoming integral revisualization tools across the industrial sector. Learn how Unit040, a company specializing in visualization and simulation, creates digital twins that combine real-time 3D technology with BIM, CAD and CAE systems to add value at all stages of the building and product lifecycle, from the early design phase to predictive maintenance using Internet of Things (IoT) data.
Speakers:
Pieter Weterings - Unit040
Guido van Gageldonk - Unit040
Watch the session on YouTube: https://youtu.be/j4i14p89h_s
What is the Digital Twin?
Digital twin is the ability to make a virtual representation of the physical elements and the dynamics of how an Internet of Things device operates and works. It's more than a blueprint, it's more than a schematic. It's not just a picture. It's a lot more than a pair of ‘virtual reality’ glasses. It's a virtual representation of both the elements and the dynamics of how an Internet of Things device responds throughout its lifecycle. It can be a jet engine, a building, process on factory floor, and much, much more.
Watch the video introduction of this keynote presentation from Genius of Things Summit in Munich https://youtu.be/RaOejcczPas
Nurturing Digital Twins: How to Build Virtual Instances of Physical Assets to...Cognizant
To embark on the digital twin jounrey, assess your readiness, define and communicate a vision, set common data management rules and build in flexibility for intelligence.
Investment Opportunities in the New Normal - AirTree VenturesMelissa Ran
The document discusses investment opportunities that have arisen from changes brought about by the COVID-19 pandemic. It outlines five key areas: 1) A remote-first world where remote work tools have grown significantly. 2) Internet models now work for sectors like healthcare and education that have been slow to adopt technology. 3) E-commerce growth that was previously years-long has accelerated to growth over months. 4) The rise of the creator economy empowering individuals. 5) Esports growing to become the new social experience as gaming culture expands. The presentation argues these trends open opportunities for startups addressing issues in a newly digital world.
A digital twin is a digital profile of a physical object or system that uses sensor data to help optimize performance. Sensors on physical objects collect data and send it to the digital twin, and the interaction between the physical object and digital twin can optimize performance through predictive maintenance. Digital twins are useful because they bridge the physical and digital worlds by translating real-world sensor data into information that can be processed digitally to help optimize businesses and systems. Examples of applications of digital twins include performance tuning, digital machine building, healthcare, smart cities, and predictive maintenance.
The annual GPU Technology Conference focused on the promising field of deep learning in 2015. And we made four major announcements that will fuel its advancement: Titan X, the world's fastest GPU; DIGITS DevBox, GPU deep learning platform; Pascal GPU architecture; NVIDIA DRIVE PX, deep learning platform for self-driving cars. The press responded to these announcements with quotes, featured in this presentation, including ones from Mashable, Forbes, re/code, and The Wall Street Journal. The week-long event was shared in astounding numbers with many blog posts and streaming keynotes.
This document discusses applications that are possible with gigabit internet speeds and localized computing infrastructure. It begins by showing current bandwidth and latency capabilities compared to applications' needs. It then describes technologies like gigabit wired/wireless networks and localized computing racks. Applications discussed include high-quality video, virtual/augmented reality, real-time sensor responses, and more. The document advocates for partnerships between cities, universities, businesses and more to develop these applications and create sustainable business models.
SIMA AZ: Emerging Information Technology Innovations & Trends 11/15/17Mark Goldstein
Mark Goldstein, International Research Center presented a big overview of Emerging Information Technology Innovations & Trends to the Society for Information Management Arizona Chapter (SIM AZ) on 11/15/17 showcasing the latest and greatest emerging technologies and novel tech innovations, highlighting the market and societal transformations underway or anticipated. It covered Advances in Computer Power and Pervasiveness; Internet of Things (IoT) Overview and Ecosystem; Mobility, Augmented Reality and Virtual Reality (AR/VR); Medical Advances Through Informatics; Artificial Intelligence (AI) and Robotics; Big Data, Its Applications and Implications; and Onward into the Future…
The CHIPS Alliance is a Linux Foundation project that develops open source hardware specifications, implementations, verification tools, and IP blocks. It aims to lower the costs of hardware development through collaboration and shared resources. Members include companies and organizations working on CPUs, interconnects, I/O, machine learning accelerators, and more. The CHIPS Alliance uses Apache 2.0 licensing to encourage IP contribution and participation while allowing commercial use of outputs. It provides a neutral environment for hardware collaboration across companies and countries.
Digital twins are precise virtual representations of physical objects that use collected data from sensors to display information. They consist of a physical object, its virtual twin, and the data connection between them. By 2021, half of large industrial companies are expected to use digital twins, improving effectiveness by 10%. Digital twins have various applications and allow real-time updates, data analysis, and product optimization. However, they require constant sensor data, large datasets, and internet connectivity to achieve full accuracy.
Digital Twin at-a-glance, Yong @SEMIforteYong Wang
Digital twins are virtual representations of physical objects or systems which are expected to proliferate greatly by 2020. They allow real-time data from sensors to be integrated into virtual models to enable optimization and self-monitoring. For manufacturing, digital twins of products, factories and performance can be created using data from design, building and operations to enable benefits like smart scheduling, preventative maintenance and maximized output. The semiconductor industry is well-positioned to benefit from digital twins as it already collects extensive operational data and has the computing power required.
NVIDIA Testimony at Senate Commerce, Science, and Transportation Committee He...NVIDIA
Rob Csongor, VP and General Manager of NVIDIA's automotive business, provides his testimony on the important subject of self-driving vehicle technology.
Fueling the Next Wave of AI Discovery - CVPR 2018NVIDIA
The CVPR annual conference showcases the most important advances in computer vision, pattern recognition, machine learning and artificial intelligence. Catch up on the top 5 announcements that came out of CVPR 2018.
The Best of AI and HPC in Healthcare and Life SciencesNVIDIA
Trends. Success stories. Training. Networking.
The GPU Technology Conference brings this all to one place. Meet the people pioneering the future of healthcare and life sciences and learn how to apply the latest AI and HPC tools to your research.
The AI Opportunity in Federal - Key Highlights from GTC DC 2018NVIDIA
Every industry will be empowered by AI from autonomous vehicles and robotics to healthcare and agriculture. The computational power that AI can provide will streamline workflows, maximize efficiencies, and open doors to new discoveries.
The document discusses preparing organizations for digital twins using IoT platforms and technologies like AI, analytics, and cloud services. It emphasizes positioning AI to augment human insights, reinventing operations with new digital data sources, and leveraging proven industrial expertise. Digital twins can provide real-time virtual representations of physical systems to improve decision making across their lifecycles using multiple data sources and models. The document recommends preparing for digital twins as part of an extensible IoT platform.
This document discusses advances in deep learning and AI through partnerships between NVIDIA and top research institutions. It summarizes that NVIDIA delivered its DGX-1 AI supercomputer to UC Berkeley and Mass General Hospital to accelerate breakthroughs in deep learning for tasks like analyzing medical data and autonomous vehicles. Applications highlighted include isolating speech from noise, predicting health risks from genes, and allowing NVIDIA to test self-driving vehicles in California.
A digital twin is a digital replica of a living or non-living physical entity. By bridging the physical and the virtual world, data is transmitted seamlessly allowing the virtual entity to exist simultaneously with the physical entity.
See: El Saddik, A. (2018). Digital Twins: The Convergence of Multimedia Technologies. IEEE MultiMedia, 25(2), 87-92.
This seminar report discusses digital twins, which create living digital simulation models of physical assets. A digital twin continuously learns and updates itself from multiple real-time data sources to represent the current status of its corresponding physical twin. The report provides definitions of different types of digital twins and discusses how GE uses digital twins for applications like asset management, operations optimization, and advanced controls. It also covers the characteristics and advantages of digital twins, as well as examples of their use in various industrial sectors.
Digital twins: the power of a virtual visual copy - Unite Copenhagen 2019Unity Technologies
From buildings and infrastructure to industrial machinery and factories, digital twins are becoming integral revisualization tools across the industrial sector. Learn how Unit040, a company specializing in visualization and simulation, creates digital twins that combine real-time 3D technology with BIM, CAD and CAE systems to add value at all stages of the building and product lifecycle, from the early design phase to predictive maintenance using Internet of Things (IoT) data.
Speakers:
Pieter Weterings - Unit040
Guido van Gageldonk - Unit040
Watch the session on YouTube: https://youtu.be/j4i14p89h_s
What is the Digital Twin?
Digital twin is the ability to make a virtual representation of the physical elements and the dynamics of how an Internet of Things device operates and works. It's more than a blueprint, it's more than a schematic. It's not just a picture. It's a lot more than a pair of ‘virtual reality’ glasses. It's a virtual representation of both the elements and the dynamics of how an Internet of Things device responds throughout its lifecycle. It can be a jet engine, a building, process on factory floor, and much, much more.
Watch the video introduction of this keynote presentation from Genius of Things Summit in Munich https://youtu.be/RaOejcczPas
Nurturing Digital Twins: How to Build Virtual Instances of Physical Assets to...Cognizant
To embark on the digital twin jounrey, assess your readiness, define and communicate a vision, set common data management rules and build in flexibility for intelligence.
Investment Opportunities in the New Normal - AirTree VenturesMelissa Ran
The document discusses investment opportunities that have arisen from changes brought about by the COVID-19 pandemic. It outlines five key areas: 1) A remote-first world where remote work tools have grown significantly. 2) Internet models now work for sectors like healthcare and education that have been slow to adopt technology. 3) E-commerce growth that was previously years-long has accelerated to growth over months. 4) The rise of the creator economy empowering individuals. 5) Esports growing to become the new social experience as gaming culture expands. The presentation argues these trends open opportunities for startups addressing issues in a newly digital world.
A digital twin is a digital profile of a physical object or system that uses sensor data to help optimize performance. Sensors on physical objects collect data and send it to the digital twin, and the interaction between the physical object and digital twin can optimize performance through predictive maintenance. Digital twins are useful because they bridge the physical and digital worlds by translating real-world sensor data into information that can be processed digitally to help optimize businesses and systems. Examples of applications of digital twins include performance tuning, digital machine building, healthcare, smart cities, and predictive maintenance.
The annual GPU Technology Conference focused on the promising field of deep learning in 2015. And we made four major announcements that will fuel its advancement: Titan X, the world's fastest GPU; DIGITS DevBox, GPU deep learning platform; Pascal GPU architecture; NVIDIA DRIVE PX, deep learning platform for self-driving cars. The press responded to these announcements with quotes, featured in this presentation, including ones from Mashable, Forbes, re/code, and The Wall Street Journal. The week-long event was shared in astounding numbers with many blog posts and streaming keynotes.
This document discusses applications that are possible with gigabit internet speeds and localized computing infrastructure. It begins by showing current bandwidth and latency capabilities compared to applications' needs. It then describes technologies like gigabit wired/wireless networks and localized computing racks. Applications discussed include high-quality video, virtual/augmented reality, real-time sensor responses, and more. The document advocates for partnerships between cities, universities, businesses and more to develop these applications and create sustainable business models.
SIMA AZ: Emerging Information Technology Innovations & Trends 11/15/17Mark Goldstein
Mark Goldstein, International Research Center presented a big overview of Emerging Information Technology Innovations & Trends to the Society for Information Management Arizona Chapter (SIM AZ) on 11/15/17 showcasing the latest and greatest emerging technologies and novel tech innovations, highlighting the market and societal transformations underway or anticipated. It covered Advances in Computer Power and Pervasiveness; Internet of Things (IoT) Overview and Ecosystem; Mobility, Augmented Reality and Virtual Reality (AR/VR); Medical Advances Through Informatics; Artificial Intelligence (AI) and Robotics; Big Data, Its Applications and Implications; and Onward into the Future…
The CHIPS Alliance is a Linux Foundation project that develops open source hardware specifications, implementations, verification tools, and IP blocks. It aims to lower the costs of hardware development through collaboration and shared resources. Members include companies and organizations working on CPUs, interconnects, I/O, machine learning accelerators, and more. The CHIPS Alliance uses Apache 2.0 licensing to encourage IP contribution and participation while allowing commercial use of outputs. It provides a neutral environment for hardware collaboration across companies and countries.
Global Technology Trends - Electronic SystemsIan Phillips
Electronic systems have become ubiquitous in modern life, powering devices in entertainment, transportation, healthcare, and more. They are the result of global collaboration between thousands of engineers and companies. While electronic technologies continue advancing rapidly, their capabilities are limited by the constraints of physics and engineering. ARM designs processor technologies that allow advanced consumer products to utilize billions of transistors efficiently. Electronic systems will continue enabling societies to address challenges around urbanization, health, energy, security and more in the 21st century.
The Ericsson HDS 8000 is a hyperscale cloud solution based on Intel's Rack Scale Architecture. It uses hardware disaggregation and pooled resources to optimize storage, computing, and networking resources. This flexible architecture improves efficiency and allows resources to be dynamically allocated based on workload demands. The solution aims to reduce costs and speeds up service delivery for data centers and telecom networks.
Ericsson introduces a hyperscale cloud solutionEricsson
All businesses are becoming software companies and all are becoming "information enabled". In the near future companies will be dependent on 10x the IT capacity yet they will not have 10x the budget to deliver it. This means the approach must change. Leveraging cloud to deliver software at a faster pace exposes the company to higher levels of risk. This means they have to burden IT with policies that slow down development efforts.
As the massive growth of information technology services places increasing demand on the datacenter it is important to re-architect the underlying infrastructure, allowing companies and end-users to benefit from an increasingly services-oriented world. Datacenters need to deliver on a new era of rapid service delivery. Across network, storage and compute there is a need for a new approach to deliver the scale and efficiency required to compete in a future where "hyperscale" is a pre-requisite.
The Ericsson HDS 8000 delivers a complete datacenter and cloud platform based on Intel® Rack Scale Architecture.
http://www.ericsson.com/spotlight/cloud
Artificial Intelligence in practice - Gerbert Kaandorp - Codemotion Amsterdam...Codemotion
In this talk Gerbert will give an overview of Artificial Intelligence, outline the current state of the art in research and explain what it takes to actually do an AI project. Using practical cases and tools he will give you insight in the phases of an AI project and explain some of the problems you might encounter along the way and how you might be able to solve them.
End-to-End Big Data AI with Analytics ZooJason Dai
The document discusses Analytics Zoo, an open-source software platform for building end-to-end big data AI applications. It provides distributed deep learning frameworks like TensorFlow and PyTorch on Apache Spark. Analytics Zoo allows seamless scaling of AI models from laptop to distributed big data and includes features like automated machine learning, time series forecasting, and serving models in production. It aims to simplify development of end-to-end big data AI solutions.
1) The document discusses digital transformation and AI at the edge for industrial applications. It describes challenges like processing vast amounts of distributed data in real-time while ensuring security and reliability with limited resources.
2) Edge computing is important for industrial IoT as it allows data processing and AI inferencing close to where data is generated, improving latency, security, and scalability. The document outlines several open source edge computing projects and technologies being developed.
3) Achieving digital transformation requires bridging gaps between IT and operational systems through approaches like collecting telemetry data, predictive maintenance, and building a data-informed culture across the organization. Standards like OPC UA are also important for interoperability.
This document provides a summary of Ray Simar Jr.'s qualifications and experience. It outlines his over 25 years of experience in the semiconductor industry and decade of experience in academia, entrepreneurship, and consulting. It highlights his pioneering work developing DSP architectures at Texas Instruments, including being the principal architect of three major DSP product lines. It also summarizes his current role as a Professor in the Practice at Rice University where he teaches and mentors students in computer engineering, digital signal processing, and neural networks fields.
Give Your Organization Better, Faster Insights & Answers with High Performanc...Dell World
From modeling and simulating new products to analyzing ‘Big Data’ for insights into customer behaviors, achieving better results faster can be crucial for competitive advantages and success. High performance computing (HPC), long used for academic/government research, has gone mainstream, and is now used by companies and organizations in all fields—from finance to pharmaceuticals, from marketing to manufacturing, from e-commerce to engineering, from healthcare to homeland defense. Dell is a leader in HPC and can help you get better, faster insights and answers, no matter what your organization desires to achieve.
STFC funds and operates world-class science infrastructure for industry, government, and academia. It has invested heavily in high performance computing (HPC) since the 1960s. Democratizing access to HPC and reducing its complexity are now key challenges to enable wider use, especially in industry. The Hartree Centre works to address this through new engagement models, visualization tools, and platforms that make HPC resources more accessible and usable for non-experts.
Supermicro AI Pod that’s Super Simple, Super Scalable, and Super AffordableRebekah Rodriguez
The worlds of HPC and AI are evolving at a tremendous rate. The demands of modern-day applications put immense pressure on local IT teams and resources. More often than not, this pressure can come from requiring an AI strategy to speed up mission-critical applications - but this can come at a cost which can hinder adoption. In this webinar, Supermicro, together with International Computer Concepts (ICC) and Define Tech, will demonstrate their AI Super Pod that delivers on AI strategy needs without breaking the bank.
TRIK cybernetical controller for advanced autonomous robotic models and embedded systems prototyping. Designed for R&D labs and startups, but perfect for STEM(STEAM) robotics.
The Implementing AI: Hardware Challenges, hosted by KTN and eFutures, is the first event of the Implementing AI webinar series to address the challenges and opportunities that realising AI for hardware present.
There will be presentations from hardware organisations and from solution providers in the morning; followed by Q&A. The afternoon session will consist of virtual breakout rooms, where challenges raised in the morning session can be workshopped.
Artificial Intelligence now impacts every aspect of modern life and is key to the generation of valuable business insights.
Implementing AI webinar series is designed for people involved in the management and implementation of AI based solutions – from developers to CTOs.
Find out more: https://ktn-uk.co.uk/news/just-launched-implementing-ai-webinar-series
Arduino, Open Source and The Internet of Things LandscapeJustin Grammens
What's this "Internet of Things (IoT)" I keep hearing all about? We will cover where IoT came from, where it is today, where it's going in the future and how the Arduino open source platform is being used to bring new ideas and products to life.
PPC64 Open ISA and A2I Core along with the PPC64 Open Hardware Notebook PCB and Libre-Soc project.
This year IBM released the A2I POWER processor core design and associated FPGA environment. In 2019 IBM opened the POWER Instruction Set Architecture (ISA). The Power Progress Community released the PCB of the Notebook Motherboard based on Power Architecture with Cern Open Hardware License. Libre-SOC is a software-hardware project that aims to deliver a physical POWER compliant SOC that comes complete with a CPU, GPU, VPU, and DDR controller. We will discover these concrete projects.
A New Direction for Computer Architecture Researchdbpublications
This paper we suggest a different computing environment as a worthy new direction for computer architecture research: personal mobile computing, where portable devices are used for visual computing and personal communications tasks. Such a device supports in an integrated fashion all the functions provided to-day by a portable computer, a cellular phone, a digital camera and a video game. The requirements placed on the processor in this environment are energy efficiency, high performance for multimedia and DSP functions, and area efficient, scalable designs. We examine the architectures that were recently pro-posed for billion transistor microprocessors. While they are very promising for the stationary desktop and server workloads, we discover that most of them are un-able to meet the challenges of the new environment and provide the necessary enhancements for multimedia applications running on portable devices.
The fight for surviving in the IoT worldRadu Vunvulea
The world is changing. Every day new devices appears around us. How will .NET survive in a word that is changing, in a word that migrates from mainstream to small and cheap devices fast and without mercy. The session will attack how .NET can survive and what are the new features of .NET that help us (the developers) to do this transition.
Similar to Implementing AI: Running AI at the Edge (20)
Competition Briefing - Open Digital Solutions for Net Zero Energy KTN
This briefing provided more information on the scope and application process for Innovate UK's Small Business Research Initiative (SBRI) competition to develop open software, hardware and data solutions that address the challenges of transforming to a net zero energy system in the UK.
An Introduction to Eurostars - an Opportunity for SMEs to Collaborate Interna...KTN
This webinar highlighted opportunities within the EUREKA Eurostars programme and how Innovate UK KTN and partners can help your business to innovate and go international.
Prospering from the Energy Revolution: Six in Sixty - Technology and Infrastr...KTN
Hear about one of the key facets of PFER, a £104m programme focussed on the integration of power, heat and transport and the business models needed to enable Smart Local Energy Systems (SLES) to scale towards net zero.
UK Catalysis: Innovation opportunities for an enabling technologyKTN
Read about how accelerating innovations in catalysis will play a vital role in enabling the UK to meet its net zero targets in the areas of hydrogen production, Power-to-X, carbon dioxide utilisation and the use of alternative feedstocks.
Industrial Energy Transformational Fund Phase 2 Spring 2022 - Competition Bri...KTN
The Phase 2 competition for England, Wales and Northern Ireland opens on the 31st January 2022 and runs until 29th April 2022 and is worth up to £60 million in funding.
Horizon Europe ‘Culture, Creativity and Inclusive Society’ Consortia Building...KTN
The proposed approach involves using a "Citizen Dialog Kit" (CDK) platform to engage citizens in conversations at public places through wireless displays and an online platform. The CDK allows conveying real-time information to citizens and surveying their viewpoints. It empowers citizens to start conversations themselves. The proposer seeks a consortium that values engaging less spontaneously engaged citizens in their neighbourhoods and communities. As a university spin-off, the proposer brings the fully functioning CDK platform, customization expertise, and experience in citizen engagement projects and urban human-computer interaction evaluation studies.
Horizon Europe ‘Culture, Creativity and Inclusive Society’ Consortia Building...KTN
This webinar highlights relevant call topics within Cluster 2 which focuses on challenges pertaining to democratic governance, cultural heritage and the creative economy, as well as social and economic transformations.
Smart Networks and Services Joint Undertaking (SNS JU) Call TopicsKTN
The document provides information about the Smart Networks and Services (SNS) topics under Horizon Europe, the EU's research and innovation programme. It outlines the main types of funding actions - Research and Innovation Actions (RIA), Innovation Actions (IA), and Coordination and Support Actions (CSA). It also summarizes the four streams of SNS topics on smart communication components, radical 6G technology, experimental infrastructure, and large-scale trials with verticals. Support resources through UK Research and Innovation and the UK NCP network are listed at the end.
Building Talent for the Future 2 – Expression of Interest BriefingKTN
This competition briefing is supporting the creation, delivery, and growth of PEMD industry-focused course content, materials, and support for skills plus training.
Connected and Autonomous Vehicles Cohort WorkshopKTN
The document provides an agenda and overview for a Connected and Autonomous Vehicles (CAV) Cohort Workshop on December 14th, 2021. The agenda includes introductions from heads of CCAV and Future Regulations discussing key outcomes and areas of focus. There will also be presentations on the state of CAV development in the UK and potential use cases. The workshop aims to facilitate discussion and networking among innovators in the CAV field.
Performance Projects specialises in niche vehicle and motorsport innovation, designing, building and supplying complex subsystems through to whole vehicles.
How to Create a Good Horizon Europe Proposal WebinarKTN
This webinar provides you with the essential hands-on knowledge and skills to transform your innovative project ideas into competitive project proposals in response to calls under Horizon Europe.
Horizon Europe Tackling Diseases and Antimicrobial Resistance (AMR) Webinar a...KTN
Innovate UK KTN Global Alliance in partnership with the Foreign, Commonwealth and Development Office (FCDO) the UK Science and Innovation Network in Ireland and the Nordics, and UK National Contact Points (NCPs) from Innovate UK (UKRI) hosted a workshop to help delegates form international collaborations and strategic partnerships.
1. The document discusses Custom Interconnect Ltd (CIL), an electronics manufacturing company that specializes in power electronics and has expanded its capabilities for GaN and SiC devices.
2. CIL has been successful in projects like GaNSiC that developed new silver sintering techniques for attaching GaN and SiC dies.
3. CIL continues to work with customers on non-funded power electronics projects and has two new funded projects starting in early 2022.
ZF is a global technology company that supplies systems for passenger cars, commercial vehicles and industrial technology, enabling the next generation of mobility. ZF allows vehicles to see, think and act. In the four technology domains Vehicle Motion Control, Integrated Safety, Automated Driving, and Electric Mobility, ZF offers comprehensive solutions for established vehicle manufacturers and newly emerging transport and mobility service providers.
FluxSys was formed in 2013, from their base in Wellesbourne, Warwickshire they support their UK and international clients with the specification, design and prototyping of a wide range of electric machines and drives.
FluxSys uses its skills, experience and independence within customers’ projects to support their electrification journeys and skills development, utilising knowledge sharing in an open & collaborative manner with like-minded clients and technical experts.
Made Smarter Innovation: Sustainable Smart Factory Competition BriefingKTN
Here are the key eligibility criteria for applicants:
- The lead applicant must be a UK registered business.
- Projects must be collaborative involving at least two organizations, including one UK SME.
- Projects must be carried out in the UK and exploit results in the UK.
- Project costs must be between £1-8 million.
- Grants cannot exceed 50% of costs for Strand 1 or 40% for Strand 2.
- Applicants can include UK businesses (small/micro, medium or large), universities and non-profit research organizations.
- Projects must apply to the correct strand - Strand 1 is data-centric while Strand 2 can focus on other digital
Driving the Electric Revolution – PEMD Skills HubKTN
Watch this briefing webinar to find out more about this new competition which supports the development of the Skills Hub, a training platform to support the PEMD sector.
Medicines Manufacturing Challenge EDI Survey Briefing WebinarKTN
In anticipation of the Medicines Manufacturing Challenge sending out an EDI survey to those involved in any projects funded under the programme, this webinar provides more context behind the request, an overview of the Innovate UK Equality, Diversity and Inclusion (EDI) programmes, and an opportunity for attendees to ask questions and get involved.
HCL Notes und Domino Lizenzkostenreduzierung in der Welt von DLAUpanagenda
Webinar Recording: https://www.panagenda.com/webinars/hcl-notes-und-domino-lizenzkostenreduzierung-in-der-welt-von-dlau/
DLAU und die Lizenzen nach dem CCB- und CCX-Modell sind für viele in der HCL-Community seit letztem Jahr ein heißes Thema. Als Notes- oder Domino-Kunde haben Sie vielleicht mit unerwartet hohen Benutzerzahlen und Lizenzgebühren zu kämpfen. Sie fragen sich vielleicht, wie diese neue Art der Lizenzierung funktioniert und welchen Nutzen sie Ihnen bringt. Vor allem wollen Sie sicherlich Ihr Budget einhalten und Kosten sparen, wo immer möglich. Das verstehen wir und wir möchten Ihnen dabei helfen!
Wir erklären Ihnen, wie Sie häufige Konfigurationsprobleme lösen können, die dazu führen können, dass mehr Benutzer gezählt werden als nötig, und wie Sie überflüssige oder ungenutzte Konten identifizieren und entfernen können, um Geld zu sparen. Es gibt auch einige Ansätze, die zu unnötigen Ausgaben führen können, z. B. wenn ein Personendokument anstelle eines Mail-Ins für geteilte Mailboxen verwendet wird. Wir zeigen Ihnen solche Fälle und deren Lösungen. Und natürlich erklären wir Ihnen das neue Lizenzmodell.
Nehmen Sie an diesem Webinar teil, bei dem HCL-Ambassador Marc Thomas und Gastredner Franz Walder Ihnen diese neue Welt näherbringen. Es vermittelt Ihnen die Tools und das Know-how, um den Überblick zu bewahren. Sie werden in der Lage sein, Ihre Kosten durch eine optimierte Domino-Konfiguration zu reduzieren und auch in Zukunft gering zu halten.
Diese Themen werden behandelt
- Reduzierung der Lizenzkosten durch Auffinden und Beheben von Fehlkonfigurationen und überflüssigen Konten
- Wie funktionieren CCB- und CCX-Lizenzen wirklich?
- Verstehen des DLAU-Tools und wie man es am besten nutzt
- Tipps für häufige Problembereiche, wie z. B. Team-Postfächer, Funktions-/Testbenutzer usw.
- Praxisbeispiele und Best Practices zum sofortigen Umsetzen
Conversational agents, or chatbots, are increasingly used to access all sorts of services using natural language. While open-domain chatbots - like ChatGPT - can converse on any topic, task-oriented chatbots - the focus of this paper - are designed for specific tasks, like booking a flight, obtaining customer support, or setting an appointment. Like any other software, task-oriented chatbots need to be properly tested, usually by defining and executing test scenarios (i.e., sequences of user-chatbot interactions). However, there is currently a lack of methods to quantify the completeness and strength of such test scenarios, which can lead to low-quality tests, and hence to buggy chatbots.
To fill this gap, we propose adapting mutation testing (MuT) for task-oriented chatbots. To this end, we introduce a set of mutation operators that emulate faults in chatbot designs, an architecture that enables MuT on chatbots built using heterogeneous technologies, and a practical realisation as an Eclipse plugin. Moreover, we evaluate the applicability, effectiveness and efficiency of our approach on open-source chatbots, with promising results.
How information systems are built or acquired puts information, which is what they should be about, in a secondary place. Our language adapted accordingly, and we no longer talk about information systems but applications. Applications evolved in a way to break data into diverse fragments, tightly coupled with applications and expensive to integrate. The result is technical debt, which is re-paid by taking even bigger "loans", resulting in an ever-increasing technical debt. Software engineering and procurement practices work in sync with market forces to maintain this trend. This talk demonstrates how natural this situation is. The question is: can something be done to reverse the trend?
Essentials of Automations: Exploring Attributes & Automation ParametersSafe Software
Building automations in FME Flow can save time, money, and help businesses scale by eliminating data silos and providing data to stakeholders in real-time. One essential component to orchestrating complex automations is the use of attributes & automation parameters (both formerly known as “keys”). In fact, it’s unlikely you’ll ever build an Automation without using these components, but what exactly are they?
Attributes & automation parameters enable the automation author to pass data values from one automation component to the next. During this webinar, our FME Flow Specialists will cover leveraging the three types of these output attributes & parameters in FME Flow: Event, Custom, and Automation. As a bonus, they’ll also be making use of the Split-Merge Block functionality.
You’ll leave this webinar with a better understanding of how to maximize the potential of automations by making use of attributes & automation parameters, with the ultimate goal of setting your enterprise integration workflows up on autopilot.
Freshworks Rethinks NoSQL for Rapid Scaling & Cost-EfficiencyScyllaDB
Freshworks creates AI-boosted business software that helps employees work more efficiently and effectively. Managing data across multiple RDBMS and NoSQL databases was already a challenge at their current scale. To prepare for 10X growth, they knew it was time to rethink their database strategy. Learn how they architected a solution that would simplify scaling while keeping costs under control.
Northern Engraving | Nameplate Manufacturing Process - 2024Northern Engraving
Manufacturing custom quality metal nameplates and badges involves several standard operations. Processes include sheet prep, lithography, screening, coating, punch press and inspection. All decoration is completed in the flat sheet with adhesive and tooling operations following. The possibilities for creating unique durable nameplates are endless. How will you create your brand identity? We can help!
How to Interpret Trends in the Kalyan Rajdhani Mix Chart.pdfChart Kalyan
A Mix Chart displays historical data of numbers in a graphical or tabular form. The Kalyan Rajdhani Mix Chart specifically shows the results of a sequence of numbers over different periods.
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectorsDianaGray10
Join us to learn how UiPath Apps can directly and easily interact with prebuilt connectors via Integration Service--including Salesforce, ServiceNow, Open GenAI, and more.
The best part is you can achieve this without building a custom workflow! Say goodbye to the hassle of using separate automations to call APIs. By seamlessly integrating within App Studio, you can now easily streamline your workflow, while gaining direct access to our Connector Catalog of popular applications.
We’ll discuss and demo the benefits of UiPath Apps and connectors including:
Creating a compelling user experience for any software, without the limitations of APIs.
Accelerating the app creation process, saving time and effort
Enjoying high-performance CRUD (create, read, update, delete) operations, for
seamless data management.
Speakers:
Russell Alfeche, Technology Leader, RPA at qBotic and UiPath MVP
Charlie Greenberg, host
For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2024/06/how-axelera-ai-uses-digital-compute-in-memory-to-deliver-fast-and-energy-efficient-computer-vision-a-presentation-from-axelera-ai/
Bram Verhoef, Head of Machine Learning at Axelera AI, presents the “How Axelera AI Uses Digital Compute-in-memory to Deliver Fast and Energy-efficient Computer Vision” tutorial at the May 2024 Embedded Vision Summit.
As artificial intelligence inference transitions from cloud environments to edge locations, computer vision applications achieve heightened responsiveness, reliability and privacy. This migration, however, introduces the challenge of operating within the stringent confines of resource constraints typical at the edge, including small form factors, low energy budgets and diminished memory and computational capacities. Axelera AI addresses these challenges through an innovative approach of performing digital computations within memory itself. This technique facilitates the realization of high-performance, energy-efficient and cost-effective computer vision capabilities at the thin and thick edge, extending the frontier of what is achievable with current technologies.
In this presentation, Verhoef unveils his company’s pioneering chip technology and demonstrates its capacity to deliver exceptional frames-per-second performance across a range of standard computer vision networks typical of applications in security, surveillance and the industrial sector. This shows that advanced computer vision can be accessible and efficient, even at the very edge of our technological ecosystem.
Digital Banking in the Cloud: How Citizens Bank Unlocked Their MainframePrecisely
Inconsistent user experience and siloed data, high costs, and changing customer expectations – Citizens Bank was experiencing these challenges while it was attempting to deliver a superior digital banking experience for its clients. Its core banking applications run on the mainframe and Citizens was using legacy utilities to get the critical mainframe data to feed customer-facing channels, like call centers, web, and mobile. Ultimately, this led to higher operating costs (MIPS), delayed response times, and longer time to market.
Ever-changing customer expectations demand more modern digital experiences, and the bank needed to find a solution that could provide real-time data to its customer channels with low latency and operating costs. Join this session to learn how Citizens is leveraging Precisely to replicate mainframe data to its customer channels and deliver on their “modern digital bank” experiences.
Ivanti’s Patch Tuesday breakdown goes beyond patching your applications and brings you the intelligence and guidance needed to prioritize where to focus your attention first. Catch early analysis on our Ivanti blog, then join industry expert Chris Goettl for the Patch Tuesday Webinar Event. There we’ll do a deep dive into each of the bulletins and give guidance on the risks associated with the newly-identified vulnerabilities.
Introduction of Cybersecurity with OSS at Code Europe 2024Hiroshi SHIBATA
I develop the Ruby programming language, RubyGems, and Bundler, which are package managers for Ruby. Today, I will introduce how to enhance the security of your application using open-source software (OSS) examples from Ruby and RubyGems.
The first topic is CVE (Common Vulnerabilities and Exposures). I have published CVEs many times. But what exactly is a CVE? I'll provide a basic understanding of CVEs and explain how to detect and handle vulnerabilities in OSS.
Next, let's discuss package managers. Package managers play a critical role in the OSS ecosystem. I'll explain how to manage library dependencies in your application.
I'll share insights into how the Ruby and RubyGems core team works to keep our ecosystem safe. By the end of this talk, you'll have a better understanding of how to safeguard your code.
zkStudyClub - LatticeFold: A Lattice-based Folding Scheme and its Application...Alex Pruden
Folding is a recent technique for building efficient recursive SNARKs. Several elegant folding protocols have been proposed, such as Nova, Supernova, Hypernova, Protostar, and others. However, all of them rely on an additively homomorphic commitment scheme based on discrete log, and are therefore not post-quantum secure. In this work we present LatticeFold, the first lattice-based folding protocol based on the Module SIS problem. This folding protocol naturally leads to an efficient recursive lattice-based SNARK and an efficient PCD scheme. LatticeFold supports folding low-degree relations, such as R1CS, as well as high-degree relations, such as CCS. The key challenge is to construct a secure folding protocol that works with the Ajtai commitment scheme. The difficulty, is ensuring that extracted witnesses are low norm through many rounds of folding. We present a novel technique using the sumcheck protocol to ensure that extracted witnesses are always low norm no matter how many rounds of folding are used. Our evaluation of the final proof system suggests that it is as performant as Hypernova, while providing post-quantum security.
Paper Link: https://eprint.iacr.org/2024/257
2. • Innovate UK drives productivity and economic growth by supporting businesses
to develop and realise the potential of new ideas, including those from the UK’s
world-class research base.
• Knowledge Transfer Network (KTN) is Innovate UK’s Network partner
• We help business to grow the economy and improve people’s lives by capturing
maximum value from innovative ideas, scientific research and creativity.
• KTN combines in-depth expertise in all sectors with the ability to cross
boundaries.
• Nigel Rix, Head of Enabling Technology: nigel.rix@ktn-uk.org
3. eFutures aims to strengthen and support a network of people
working in electronic systems across the UK
• Building new links and increasing involvement with industry
• Mapping the national electronics research, to ensure the work across the UK is known and noted
• Encouraging and funding innovative multi-disciplinary/multi-university proposals
• Working to improve, encourage and support equality, diversity and inclusion across our sector
• Communicating with our network via a monthly magazine & social media
• Running regular events that support our network & strategy
• Launching a Big Ideas Challenge
Twitter @efuturesuk
Sign up to our mailing list: efutures@qub.ac.uk
4. Next webinar: Friday 3rd July
Vision & Imaging Systems
AI: Vision Systems
Speakers include Xilinx; University of Edinburgh;
Sensing Feeling and AAEON Technology
7. 3
THE AIOT IS APPLICABLE ACROSS MARKETS
ENABLING HIGH PERFORMANCE, ACROSS VERTICALS, ECONOMICALLY
Smart speaker
Audio visual
Appliances
Lighting
Security
Fitness
Care
Diagnostics &
monitoring
MHealth
Traffic &
parking
Environmental
Utilities
Public safety &
security
TAM
Operations
Tracking
Safety
Maintenance
Energy
management
Asset tracking &
predictive
maintenance
In car people
tracking
Autonomous L1
driving & safety
500M
UNITS
500M
UNITS
650M
UNITS
450M
UNITS
90M
UNITS
8. 44
CHALLENGES OF THE AIoT REVOLUTION
45% DATA SECURITY AND AUTONOMY
38% BANDWIDTH
32% LATENCY
24% SCALABILITY
24% CLOUD INFRASTRUCTURE LIMITATIONS
BASED ON PRIMARY RESEARCH WITH ELECTRONICS ENGINEERS
9. WHAT’S NEEDED?
AIoT devices demand a processor with
high-performance compute, efficient energy
usage and a low eBOM.
10. A NEW KIND OF PROCESSOR
Fast, flexible and economical, xcore.ai puts
intelligence at the core of smart products,
combining AI, DSP, control and IO compute
in a one dollar device.
11. 77
FAST, FLEXIBLE AND ECONOMICAL
32 x 16 x
15 x 21 x
ARM Cortex M7 @ 600MHzxcore.ai
AI performance faster I/O processing
DSP performance more 16-bit MACs
Benchmarked 18 Nov 2019. Preliminary information subject to change without notice
DELIVERING STANDOUT PERFORMANCE
12. 88
FLEXIBLE & SCALABLE ARCHITECTURE
DRIVING FAST TIME TO MARKET, ENABLING COST EFFECTIVE SOLUTIONS
xcore device families
xcore Tools
xcore Libraries
3rd Party
Libraries
xcore LibrariesFreeRTOS
Custom platform solutions
xcore Libraries
USB
Audio
Voice
Human
Presence
Smart
Home
Connect
Health
Smart
Mobility
IndustryIoT
SmartCities
Solutions
13. 99
STATE OF THE ART ARCHITECTURE
HIGH PERFORMANCE AND ENERGY EFFICIENCY CONVERGE IN A LOW eBOM CLASS LEADER
c
hardware ports
IO pins
switch
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xtime scheduler
hardware ports
xtime scheduler IO pins
SRAMSRAM
ALU (FP + int)
vector unit
ALU (FP + int)
vector unit
High-Speed USB PHY MIPI D-PHY
external
LPDDR
interface
JTAG
core PLL
app
PLL
OTP OTP
oscillator reset16 real-time logical cores,
with support for scalar /
float / vector instructions
Vector processing unit,
supports 8-bit and binarised
neural network inferences
Extended memory support
for large applications
Flexible IO ports with
nano-second latency;
create interfaces in software
High performance instruction
set for DSP, ML and
cryptographic functions
Integrated MIPI interface
for imaging support
Example software tasks
14. 1010
MAPPING REAL-TIME TASKS, APP TASKS, AND INFERENCING TASKS
Neuralnetmodel
c
Hardware Ports
IO pins
Switch
xTIME scheduler
Hardware Ports
xTIME scheduler IO pins
High speed USB PHY MIDI D-PHY
External
LPDDR
interface
JTAG
Core PLL App PLL
Oscillator Reset
FreeRTOS and app
tasks dynamically
share fixed number of
thread contexts
Inferencing and real time tasks
allocated fixed threads at compile time
I2SLEDdrivers
PDMPDM
c
Far-fieldmicrophone
processing
Applicationtask
Applicationtask
…
Applicationtask
Keyworddetection
FreeRTOS
I2C
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
xcore logical core
Internal
SRAM
Internal
SRAM
ALU (FP + int)
Vector unit
ALU (FP + int)
Vector unit
OTP OTP
PDM
Far-field microphone
processing
Keyword detection
Free
RTOS
I2S, I2C, LED drivers
Apptask
PDM
Apptask
Apptask
Apptask
Neural net model
15. 1111
FOUR CLASSES OF COMPUTE, ONE DEVELOPMENT PLATFORM
“USING XMOS WE WERE ABLE TO REPLACE THREE SEPARATE DEVELOPMENT SYSTEMS”
Richard Hollinshead, Meridian
Embedded
code
DSP
code
NN
Model
Cortex-M DSP core NPU Hardware
gates
IO &
accelerators
Cortex SoC development
Embedded
code
DSP
code
NN
Model
xcore
IO &
accelerators
xcore development
16. 1212
PROGRAMMABLE USING INDUSTRY STANDARD TOOLS
ENABLING RAPID DEPLOYMENT AND SHORTENING TIME TO MARKET
Example software tasks
• Industry-standard TensorFlow Lite
workflow
• Automatic model translation
• Community support
Applicationtask
Applicationtask
…
Applicationtask
FreeRTOS
• Familiar, real-time, industry-standard
development environment
• Community support
• Wide variety of third party applications
FFT
FFT
QSPI
Filter
Filter
• High performance, predictable DSP
• Accessed using industry standard tools
• Highly optimised library kernels access
xcore.ai processing
CONTROL AI DSP
17. 1313
AI USER WORKFLOW
Trained floating
point network
Lite convertor
(python API)
Run TFL to
xcore.ai
convertor
Key
TensorFlow component
XMOS component
User component
Key
TensorFlow component
XMOS component
User component
ONNX componentAlternative framework flow
trained network
my_model.tflite to TensorFlow
convertor
xcore.ai
micro Runtime
my_model.tflite
lib_xs3_ai
18. 1414
PROGRAMMING – PULLING IT ALL TOGETHER
xmos
compiler
3rd party
Libraries
Executable
Control
source code
Neural net
model
Dataflow
source code
XMOS
Libraries
TensorFlowLite
to xcore.ai
convertor
Applicationtask
Applicationtask
…
Applicationtask
FreeRTOS
FFT
FFT
QSPI
Filter
Filter
19. 1515
IN SUMMARY
• The AIoT industry has reached a tipping point that will
radically transform our way of life
• Success depends on being able to drive one of the most
impressive feats of electronics engineering
• xcore.ai is that feat
21. 1
Adapting AI to Available Resource
in Mobile/Embedded Devices
Geoff Merrett
Implementing AI: Running AI at the Edge
12 June 2020 | KTN & eFutures Online Webinar
spatialml.net
22. 2
WHY AI AT THE EDGE?
Data Privacy
• Increased privacy if data never leaves the edge
Sending data to a central location consumes energy. Once there, the
temptation is great to keep crunching them 1
Network Latency/Bandwidth/Connectivity
• Cloud AI requires good networking
Self-driving cars need very fast-reacting connections and cannot
risk being disconnected; computing needs to happen in the car itself 1
Traffic lights in Las Vegas generate 60 terabytes a day (10% of the
amount Facebook collects in a day) 1
• (the edge must fulfil requirements instead though!)
1 https://www.economist.com/special-report/2020/02/20/should-data-be-crunched-at-the-centre-or-at-the-edge
“
“
“ ”
23. 3
WHY AI AT THE EDGE?
Power Consumption of AI
• Cloud AI consumes considerable natural resource.
The carbon footprint of training a single AI is up to 284 tonnes of
CO2 equivalent – 5x the lifetime emissions of an average car 2
An estimate puts the energy used to train the model at over 3x the
yearly consumption of the average American 3
From the earliest days, the amount of computing power required
by the technology doubled every two years. But from 2012
onwards, the computing power required for today’s most-vaunted
machine-learning systems has been doubling every 3.4 months 3
• An indirect benefit of moving computation to the
edge, is that it has to be more efficient
2 https://www.newscientist.com/article/2205779-creating-an-ai-can-be-five-times-worse-for-the-planet-than-a-car/
3 https://www.theguardian.com/commentisfree/2019/nov/16/can-planet-afford-exorbitant-power-demands-of-machine-learning
“
“
”
“
24. 4
PERFORMANCE METRICS
Inference at the Edge (/End)
• Connectivity, latency; privacy…
• …but constrained platforms
Inference
Test Data
result Inference
Trained
model
Servers Servers
Training
Xun, Lei, Tran-Thanh, Long, Al-Hashimi, Bashir and Merrett, Geoff (2020) Optimising Resource Management for Embedded Machine Learning. In Design, Automation and Test in Europe Conference 2020 (DATE'20).
25. 5
EMBEDDED AI ACCELERATION
• General/specialist compute units for AI rapidly increasing
• Some mobile/embedded AI systems are
reasonably static…
• …however, others aren’t
– General purpose systems
– Multi-tenant systems
– ‘Adaptive’ AI/event-driven operation
– etc
26. 6
• Complexity of hardware-software interaction has grown
• Managing resources is no longer
trivial, yet is increasingly needed
1 CPU
Core
SYSTEM RESOURCE MANAGEMENT
n CPU1
Cores
n GPU
Cores
n FPGA
Cores
n CPU2
Cores
n T/NPU
Cores
n Device
Variants
n
Workloads
Samsung Exynos 5422 Xilinx Zynq Ultrascale+
HiSiliconKirin9905G
NVIDIA
Xavier NX
27. 7
DESIGN-TIME CHALLENGES
PlatformDiversity
How can we develop DNN models that can:
1. operate across a wide range of different
heterogeneous platforms, and
2. meet diverse application requirements?
• Existing design-time approaches such
as static model pruning compress the
model to approximately the ‘right size’.
Xun, Lei, Tran-Thanh, Long, Al-Hashimi, Bashir and Merrett, Geoff (2020) Optimising Resource Management for Embedded Machine Learning. In Design, Automation and Test in Europe Conference 2020 (DATE'20).
28. 8
RUN-TIME CHALLENGES
WorkloadDiversity
How can we perform inference while:
1. meeting timing requirements?
2. meeting power/energy requirements?
3. meeting accuracy requirements?
How can we do this:
• while executing another DNN model at
the same time?
• while executing other foreground/
background tasks at the same time?
We need dynamic DNNs…
Xun, Lei, Tran-Thanh, Long, Al-Hashimi, Bashir and Merrett, Geoff (2020) Optimising Resource Management for Embedded Machine Learning. In Design, Automation and Test in Europe Conference 2020 (DATE'20).
CPU
Type1
CPU
Type2
GPU
CPU
Type1
CPU
Type1
CPU
Type1
CPU
Type2
CPU
Type2
CPU
Type2
NPU
DNN 1 DNN 2 VR/AR
30. 10
DYNAMIC DNNs
ExperimentalSetup
Model: Modified AlexNet (~320kB)
Dataset: CIFAR10
– 32*32*3 images in 10 classes
– 50,000 training and 10,000 testing images
Framework: Caffe
Hardware:
• Odroid XU3
– CPU: 4x Arm A15 ( f = 0.2–2 GHz ) + 4x Arm A7 ( f = 0.2–1.4 GHz )
– GPU: Mali-T628 ( not used in these experiments )
• Nvidia Jetson Nano
– CPU: 4x Arm A57 ( f = 0.9, 1.4 GHz )
– GPU: 128x CUDA core Maxwell ( f = 0.6, 0.9 GHz )
Xun, Lei, Tran-Thanh, Long, Al-Hashimi, Bashir and Merrett, Geoff (2020) Incremental Training and Group Convolution Pruning for
Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms. In Workshop on Machine Learning for CAD (MLCAD’19).
31. 11
DYNAMIC DNNs
Results:DVFSandTaskMapping(OdroidXU3)
Energy Consumption Top-1 Accuracy
Xun, Lei, Tran-Thanh, Long, Al-Hashimi, Bashir and Merrett, Geoff (2020) Incremental Training and Group Convolution Pruning for
Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms. In Workshop on Machine Learning for CAD (MLCAD’19).
33. 13
DYNAMIC DNNs
Results:DVFSandTaskMapping(JetsonNano)
Energy Consumption Top-1 AccuracyEnergy Consumption
Xun, Lei, Tran-Thanh, Long, Al-Hashimi, Bashir and Merrett, Geoff (2020) Incremental Training and Group Convolution Pruning for
Runtime DNN Performance Scaling on Heterogeneous Embedded Platforms. In Workshop on Machine Learning for CAD (MLCAD’19).
34. 14
RUNTIME POWER MANAGEMENT
www.prime-project.org
Runtime Management (RTM)
• System software to react and predict
• Controls/’knobs’
• ‘Monitors’/sensors
RTM to coordinate/balance…
• Mapping to heterogeneous PEs
• Response to environmental factors
• Power consumption/battery life
• (concurrently) Executing tasks
• Application(s) requirements
• User requirements/QoE
Bragg, Graeme McLachlan, Leech, Charles R., Balsamo, Domenico, Davis, James J., Weber Wachter, Eduardo, Merrett, Geoff, Constantinides, George A. and Al-Hashimi, Bashir (2018) An application- and platform-agnostic
control and monitoring framework for multicore systems. 3rd International Conference on Pervasive and Embedded Computing, Portugal. 29 - 30 Jul 2018.
35. 15
CONCLUSIONS
• AI is moving to the edge…
If machine learning is going to be deployed at a global
scale, most of the computation will have to be done in
users’ hands, ie in their smartphones 3
• …but available resources on edge platforms
are typically both constrained and time-varying
• We need improved approaches to manage
resources in systems while providing
acceptable performance
Companies will learn to make trade-offs between
accuracy and computational efficiency, though that will
have unintended, and antisocial, consequences too 3
3 https://www.theguardian.com/commentisfree/2019/nov/16/can-planet-afford-exorbitant-power-demands-of-machine-learning
Photo by Patrick Schneider on Unsplash
“
“
”
36. 16
ACKNOWLEDGEMENTS
Lei Xun (PhD student)
w https://www.ecs.soton.ac.uk/people/lx2u16
@XunLei_CHN
spatialml.net
International Centre for Spatial Computational Learning (EPSRC)
w https://spatialml.net/
@spatialmlnet
Power and Reliability in Many-Core Embedded Systems (EPSRC)
w https://www.prime-project.org
@prime_programme
37. 17
YOUR QUESTIONS
Professor Geoff Merrett
Head of Centre for IoT and Pervasive Systems
e: gvm@ecs.soton.ac.uk
w: www.geoffmerrett.co.uk
@g_merrett
39. Andrew Swirski,
Founder and Executive Director,
a.swirski@beetlebox.org
Real Time Low Latency Computer Vision
Unit 1. 10,
Chester House,
Kennington Park,
1-3 Brixton Road,
London,
SW9 6DE
40. • Meeting the increasing demands of Computer Vision
• What are FPGAs and why do they perform better than
CPUs
• Why in previous years FPGAs have been restricted to
hardware engineers
• The new generation of Xilinx software development tools:
• Vitis Unified Software Development platform
• Vitis Vision Library
• Vitis AI
• ClickCV: Beetlebox’s computer vision library
• Electronic Image Stabilisation with Sundance
• Getting involved with our Early Access
Introduction
41. Our vision of the future puts enormous
demand on embedded devices to understand
the world around them
Autonomous delivery drone
Our vision of the future
42. What do we mean by high performance?
1. Throughput:
• Achievable Resolution
• Achievable Frames Per Second (FPS)
2. Latency:
• Consistent end-to-end latency
3. Power Consumption:
• Battery Life
• Heat Production
What is high performance?
45. What happens on a FPGA
int main() {
int a[5], b[5], output[5];
for(int i=0;i<5;i++){
output[i]=a[i]+b[i];
}
} + +
a[0] b[0] a[1] b[1] a[2] b[2] a[3] b[3] a[4] b[4]
+ + +
output[0] output[1] output[2] output[3] output[4]
• Control over the design
• Control over the latency
• Control over the clock (power consumption)
46. With great control comes great responsibility
• Need hardware specialists:
• Hardware Description Languages: Verilog or VHDL
• Design and Verification is a time-consuming
process
• Newer tools (High Level Synthesis) do allow for
the uses of C/C++, but:
• Limited subset of C
• No standard libraries
• Need to still understand the hardware
Restricted to Hardware Engineers
47. The new generation of tools are now focused on System-on-
Chip (SoC)
• Xilinx’s Zynq series and the Zynq Ultrascale+ series contain
ARM cores
• Benefits of a CPU host code + FPGA accelerated code
The new generation of tools
CPU FPGA
48. Providing a familiar software development
environment
• Develop, compile and debug code using C, C++ or OpenCL
either through the provided IDE or using a makefile build
flow
• Embedded platforms run a version of Linux known as
PetaLinux
• Use Standard Libraries and Tools such as GStreamer,
OpenCV and FFMPEG
• Gain access to open-source Xilinx Vitis Accelerated
Libraries
Xilinx Vitis Unified Software Platform
49. Vitis Vision library provides a library of low-
level computer vision kernels
• Provides a strong video pipeline framework
• Great for forming basic pipelines: e.g. colour thresholding
Xilinx Vitis Vision Library
CPU FPGA CPU
Collect
Data
Computer
Vision
Pipeline
Output
Data
30 FPSVideo
In
50. What we can do with Vitis Vision
Xilinx Vitis Vision Library
Edge Detection Colour Detection
51. Allows the deployment of models from deep
learning frameworks such as Tensorflow and
Caffe on to a specialized processor
• Optimizes your model to run on FPGAs:
• Prune
• Quantisation
Xilinx Vitis AI Development Environment
CPU FPGA CPU
Collect
Data Pre-process
Output
Data
30 FPSVitis AI
DPU
52. What we can do with Vitis AI
Xilinx Vitis AI
Object prediction Bounding Boxes Semantic Segmentation
53. High performance, high level FPGA kernels without the need
for hardware expertise
• Provides high-level, out-of-the-box functionality using
software only to get computer vision developed faster
• Also provides the low-level kernels needed to build
custom systems or for building test systems
• Integrates with industry standard software such as
OpenCV and GStreamer
Beetlebox ClickCV: Accelerated Computer Vision
54. Partnered with Sundance Microprocessor technologies
• Robotics and vision hardware experts
• Robots and drones often suffer from
shaky camera, especially when there
is no room or power for a gimbal
• Cameras with in-built stabilization,
such as GoPros are often impractical
• Stabilise video purely through the
video itself
• No sensor data
Electronic Image Stabilisation (EIS)
VCS-1
56. Currently running the ClickCV Early Access Programme
• High Performance with no need for computer vision hardware
specialists:
• Out-of-the-box functionality
• We can develop bespoke hardware for a specific solution
• Provide custom systems to get testing on FPGAs up and
running fast
• Let your software engineers use industry-standard tools, such
as OpenCV, GStreamer and FFMPEG
• Areas where we are looking next:
• Super Resolution
• Template Matching
• SLAM
• Deep Learning
ClickCV Early Access
57. Our Team
Andrew Swirski
MD
• MEng Electronic
Engineering at Imperial
College London
• Design Engineer at Intel
Matthew Simpson
Head of Systems
Dr Christos-Savvas Bouganis
Consultant
• Reader and Director of the
Integrated Digital Systems Lab
at Imperial College:
• Computer Vision, Image
Processing, Machine Learning
and SLAM on FPGAs
• MSc Electronic
Engineering at Imperial
College London
• CMOS Engineer at NXP
Ashley Unitt
Advisor
• CTO and CSO of
NewVoiceMedia, a SaaS
contact centre tech provider
• Acquired by Vonage
Peter Collins
Advisor
• CEO of Permasense Ltd-
sensor systems; acquired by
Emerson
• Chairman Inflowmatix Ltd
• Chariman Guided Ultrasonics
Ltd
Dr Marlon Wijeyasinghe
Head of HLS
• PhD in Electronic
Engineering at Imperial
College London
58. Contribute back and grow the community
• Technical tutorials: Vitis Vision Library tutorial:
• https://beetlebox.org/getting-started-with-computer-vision-for-
vitis-embedded-systems/
• Explainer articles: What is Computer Vision and why are
Neural Networks so important:
• https://beetlebox.org/what-is-computer-vision-and-why-are-
neural-networks-important/
• Soon launching a tutorial on Vitis AI, where we explore
sign language recognition
• Open Source
• Soon launching our github.io page:
• beetlebox.github.io
Free resources
59. • Previously FPGAs have always been a powerful but
obscure chip that only a few hardware specialists can use
• With Xilinx’s new focus on SoCs and Vitis software
development environment, embedded FPGAs have never
been more accessible
• ClickCV Computer Vision library provides out-of-the-box
high performance functionality allowing the fast
development of systems without the need for hardware
expertise
• Currently running an Early Access Programme. Come talk
to us!
• Check out our website
Conclusion
60. Andrew Swirski,
Founder and Executive Director,
a.swirski@beetlebox.org
Any Questions?
Unit 1. 10,
Chester House,
Kennington Park,
1-3 Brixton Road,
London,
SW9 6DE
61. EDGE AI CASE-STUDY:
RADAR GESTURES
W W W . I M A G I M O B . C O M
ALEXANDER SAMUELSSON, CTO/CO-FOUNDER
JUNE 2020
62. • Specialized in Edge AI
• Experience from 20+ Edge AI customer projects
• We offer
• Imagimob AI – Software-tools-as-a-Service
• Edge AI expertise
• Based in Stockholm, Sweden
W W W . I M A G I M O B . C O M
Imagimob AI
Edge AI | Software-tools-as-a-Service | Deep learning
GestureRecognitiononTheEdge|2020
Introduction Imagimob
63. • What is Edge AI?
• Imagimob AI
• Case study – radar gestures in earphones
• Edge AI opportunities for the future
W W W . I M A G I M O B . C O M
Imagimob AI
Edge AI | Software-tools-as-a-Service | Deep learning
GestureRecognitiononTheEdge|2020
What I will talk about
64. So, WHAT IS
EDGE AI?
W W W . I M A G I M O B . C O M
COMPANYPRESENTATION||JUNE2019
Placing AI at the very Edge of the network
• Where data is collected
• Autonomous
• Real time
• Low power
• Strong privacy
• We are democratizing Edge AI
Cloud aggregated raw data
• Needs connection
• High latency
• High communication cost
• High power consumption
• Weak Privacy
EDGE AI Cloud aggregated
curated data
• Autonomous
• Real time
• Low communication cost
• Low power consumption
• Strong privacy
CLOUD AI
RAW DATA
65. EDGE AI APPLICATION DEVELOPMENT
IMAGIMOB AI SUPPORTS THE FULL CYCLE FROM DATA COLLECTION TO FINISHED
EDGE AI APPLICATION
W W W . I M A G I M O B . C O M
COMPANYPRESENTATION||2019
DATA COLLECTION &
LABELLING
DATA MANAGEMENT
MODEL BUILDING
PREPARED FOR EDGE
MODEL EVALUATION EDGE OPTIMIZATION AND
VERIFICATION
APPLICATION PACKAGING
Imagimob Capture
(Android + Sensor)
MCUTraining Service
(Cloud)
Imagimob Studio
(PC)
Imagimob Studio
(PC)
Imagimob Studio
(PC)
Train
Validation
Test
66. Lot’s of applications depending on sensors
• Predictive maintenance
• Anomaly detection
• Human activity recognition
• Wake-word detection (Hi Alexa)
• …
Radar + Edge AI
• Material or surface recognition
• Detect deviations/defects in manufacturing
• Object detection
• Detect hand gestures in headphones
W W W . I M A G I M O B . C O M
Imagimob AI
Edge AI | Software-tools-as-a-Service | Deep Learning
GestureRecognitiononTheEdge|2020
What can you do with Edge AI?
67. • Working proof of concept shown at CES with Acconeer
• Application running in real time on the actual radar module
• ARM-Cortex M4 processor with only 256KB shared with BLE
stack, firmware, other applications.
• Impossible without Edge AI, the data generated by the sensor
and the almost infinite variations in how a gesture can be
performed demands an AI solution.
• Sending the data off device would drain the battery and be
impossible over bluetooth
W W W . I M A G I M O B . C O M
Imagimob AI
Edge AI | Software-tools-as-a-Service | Deep Learning
GestureRecognitiononTheEdge|2020
Radar gestures in headphones
68.
69. W W W . I M A G I M O B . C O M
Imagimob AI
Edge AI | Software-tools-as-a-Service | Deep Learning
GestureRecognitiononTheEdge|2020
Challenge #1 – Data collection
USB
WIFI
Acconeer radar
70. W W W . I M A G I M O B . C O M
GestureRecognitiononTheEdge|2020
71. Radar output: 30 KB data per second
Model predictions: 14.3 Hz
W W W . I M A G I M O B . C O M
Imagimob AI
Edge AI | Software-tools-as-a-Service | Deep Learning
GestureRecognitiononTheEdge|2020
Challenge #2 - Preprocessing
Learned
Preprocessing
Manualpreprocessing
Avg FFT
Hanning
Window
Abs Sum
Sliding
Window
72. W W W . I M A G I M O B . C O M
GestureRecognitiononTheEdge|2020
73. • Testing and verifying Edge AI models is a REAL pain
• To test on device you would have to go all the way to C code
• Moreover you would have to reflash the firmware of your headphones
• To get a really good test we would have to do this on several headphones in different locations
multiple times each week
W W W . I M A G I M O B . C O M
Imagimob AI
Edge AI | Software-tools-as-a-Service | Deep Learning
GestureRecognitiononTheEdge|2020
Challenge #3 – Testing and verifying
74. W W W . I M A G I M O B . C O M
GestureRecognitiononTheEdge|2020
75. W W W . I M A G I M O B . C O M
GestureRecognitiononTheEdge|2020
76. • End-to-end
• We have solutions to the major problems
• Data collection
• Model evaluation/testing
• Computation designed for the Edge all the way
W W W . I M A G I M O B . C O M
Imagimob AI
Edge AI | Software-tools-as-a-Service | Deep Learning
GestureRecognitiononTheEdge|2020
How are we different?
77. W W W . I M A G I M O B . C O M
Imagimob AI
Edge AI | Software-tools-as-a-Service | Deep Learning
GestureRecognitiononTheEdge|2020
The future (opportunities)
78. THANK YOU
W W W . I M A G I M O B . C O M
FOLLOW US
@imagimob
@samuelsson_al
SIGN UP FOR OUR IMAGIMOB AI EARLY ACCESS PROGRAM
GET IMAGIMOB AI FOR A FULL MONTH + EDUCATION
LIMITED SEATS
JOIN THE WORKSHOP LATER TODAY