Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Como criar um mundo autônomo e conectado - Jomar Silva

54 views

Published on

Jomar Silva - Technical Evangelist, Intel

A evolução das tecnologias de hardware, software e comunicação nos últimos anos permite projetar um novo mundo digital, autônomo e conectado.
A Internet das Coisas quando utilizada em conjunto com Inteligência Artificial propiciam um novo patamar de aplicações autônomas e conectadas, que serão a base para a criação deste novo mundo digital.
O grande desafio neste novo cenário é o imenso volume de dados que precisa ser capturado e processado em tempo real para permitir o desenvolvimento de soluções como carros autônomos e sistemas automáticos de segurança baseado em monitoramento por vídeo.
Na palestra iremos abordar estes desafios técnicos, Internet das Coisas, Inteligência Artificial, Visão Computacional, arquiteturas base para o desenvolvimento de soluções autônomas end-to-end e sobre tecnologias e produtos de hardware e software da Intel que podem te ajudar a enfrentar estes desafios de forma otimizada.
Serão abordados diversos projetos de software Open Source, bem como repositórios de soluções de código aberto que poderão ser utilizados para acelerar o aprendizado do desenvolvedor neste novo mundo digital, autônomo e conectado.

Apresentado no InterCon 2018 - https://eventos.imasters.com.br/intercon

Published in: Technology
  • Be the first to comment

  • Be the first to like this

Como criar um mundo autônomo e conectado - Jomar Silva

  1. 1. Jomar Silva Technical Evangelist
  2. 2. Intel’s compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness or any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice. Notice Revision #20110804 2
  3. 3. Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration. No computer system can be absolutely secure. Check with your system manufacturer or retailer or learn more at www.intel.com. Performance estimates were obtained prior to implementation of recent software patches and firmware updates intended to address exploits referred to as "Spectre" and "Meltdown." Implementation of these updates may make these results inapplicable to your device or system. Cost reduction scenarios described are intended as examples of how a given Intel-based product, in the specified circumstances and configurations, may affect future costs and provide cost savings. Circumstances will vary. Intel does not guarantee any costs or cost reduction. This document contains information on products, services and/or processes in development. All information provided here is subject to change without notice. Contact your Intel representative to obtain the latest forecast, schedule, specifications and roadmaps. Any forecasts of goods and services needed for Intel’s operations are provided for discussion purposes only. Intel will have no liability to make any purchase in connection with forecasts published in this document. ARDUINO 101 and the ARDUINO infinity logo are trademarks or registered trademarks of Arduino, LLC. Altera, Arria, the Arria logo, Intel, the Intel logo, Intel Atom, Intel Core, Intel Nervana, Intel Xeon Phi, Movidius, Saffron and Xeon are trademarks of Intel Corporation or its subsidiaries in the U.S. and/or other countries. *Other names and brands may be claimed as the property of others. Copyright 2018 Intel Corporation. 3
  4. 4. This document contains information on products, services and/or processes in development. All information provided here is subject to change without notice. Contact your Intel representative to obtain the latest forecast, schedule, specifications and roadmaps. Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Learn more at intel.com, or from the OEM or retailer. No computer system can be absolutely secure. Tests document performance of components on a particular test, in specific systems. Differences in hardware, software, or configuration will affect actual performance. Consult other sources of information to evaluate performance as you consider your purchase. For more complete information about performance and benchmark results, visit http://www.intel.com/performance. Cost reduction scenarios described are intended as examples of how a given Intel-based product, in the specified circumstances and configurations, may affect future costs and provide cost savings. Circumstances will vary. Intel does not guarantee any costs or cost reduction. Statements in this document that refer to Intel’s plans and expectations for the quarter, the year, and the future, are forward-looking statements that involve a number of risks and uncertainties. A detailed discussion of the factors that could affect Intel’s results and plans is included in Intel’s SEC filings, including the annual report on Form 10-K. The products described may contain design defects or errors known as errata which may cause the product to deviate from published specifications. Current characterized errata are available on request. Performance estimates were obtained prior to implementation of recent software patches and firmware updates intended to address exploits referred to as "Spectre" and "Meltdown." Implementation of these updates may make these results inapplicable to your device or system. No license (express or implied, by estoppel or otherwise) to any intellectual property rights is granted by this document. Intel does not control or audit third-party benchmark data or the web sites referenced in this document. You should visit the referenced web site and confirm whether referenced data are accurate. Intel, the Intel logo, Pentium, Celeron, Atom, Core, Xeon, Movidius, Saffron and others are trademarks of Intel Corporation in the U.S. and/or other countries. *Other names and brands may be claimed as the property of others. © 2018 Intel Corporation. 4
  5. 5. Internet of Things Artificial Intelligence Connected & Autonomous World 5
  6. 6. Internet of Things Artificial Intelligence Connected & Autonomous World 6
  7. 7. 200% growth of information-based products & services by 2020 compared with traditional product & services¹ 62% developers deem IoT ‘very important’ to digital strategies¹ 1. IDC – Digital Transformation Predictions (source) 2. NLC – Cities and Innovation Economy: Perceptions of Local Leaders (source) 3. DataAge 2025, (link) 4. Forbes, December 10, 2017 (link) >55% percentage of all data forecast to be generated by IoT in 2025.³ >$300B annual B2B IoT revenue, led by industrial sector ⁴ 66% of cities have invested in some type of smart city technology² 7
  8. 8. Optimizing Productivity Driving efficiency Lowering cost Saving Lives Improving QualityofLife Growing yield increase Security Protectingthe planet 8
  9. 9. CONNECTED SMART AUTONOMOUS 9
  10. 10. 1. Amalgamation of analyst data and Intel analysis. 2. IDC FutureScape: Worldwide Internet of Things 2017 Predictions (link) 3. IDC FutureScape: Worldwide Internet of Things 2015 Predictions (link) 50% 45% of data will be stored, analyzed, and acted on at the edge22018 2019 of IoT deployments will be network constrained3 By2020 Average internetuser 1.5GB data/day Smart hospital 3TB data/day Autonomous automobile 4TB data/day Connected airplane 40TB data/day Smart factory 1PB data/day 10 10
  11. 11. Things Network Infrastructure Data Center/CloudEdgeCompute 11
  12. 12. SoftwareEnablement CommonandSeamlessDeveloperExperience Other names and brands may be claimed as the property of others. Workload Accelerators Connectivity 12
  13. 13. Single function Single function Digital Display Digital Display Plus Camera Smart Vending Digital Surveillance Virtual Banking WI-FI Hotspots Digital Signage Single function ATM Vending Machine Digital Surveillance 13
  14. 14. AutonomousVehicles ResponsiveRetail Manufacturing EmergencyResponse Financialservices MachineVision Cities/transportation Publicsector 14
  15. 15. SmartCameras VideoGateways/NVRs Datacenter/Cloud FPGAsolutionsfromintel CV Intel®MediaSDK, OPENVINOTM Industry’sBroadestMediaandComputerVisionandDeepLearningPortfolio 15
  16. 16. Internet of Things Artificial Intelligence Connected & Autonomous World 16
  17. 17. DataAnalyticsneedsai Descriptive Analytics Diagnostic Analytics Predictive Analytics Prescriptive Analytics Cognitive Analytics Operational Analytics Advanced Analytics EmergingToday Self-Learning and Completely Automated Enterprise Simulation-Driven Analysis and Decision-Making Foresight What Will Happen, When, and Why Insight What Happened and Why Hindsight What Happened AI Datadeluge COMPUTEbreakthrough Innovationsurge
  18. 18. Source: Forrester Research – Artificial Intelligence: Fact, Fiction. How Enterprises Can Crush It; What’s Possible for Enterprises in 2017 Aiadoptionisjustbeginning 58% of business and technology professionals said they're researching AI, but only… 12%said they are currently using AI systems. In a recent Forrester Research survey…
  19. 19. Machinelearning DeepLearning Example Features  Detect similarities & anomalies in sea of data  Large, diverse dataset  Fully-explainable  Real-time updates  Practical to ‘reverse engineer’  Tabular/limited dataset  Good enough accuracy  Fully-explainable  Difficult problem to ‘reverse engineer’  Large, uniform dataset  Highest accuracy Other examples Credit fraud detection Issue and defect triage Predictive maintenance  Regression  Anomaly detection  Feature extraction  Image/speech recognition  Natural language processing (NLP)  Pattern detection MULTIPLEapproachestoAI Anti-Money Laundering Facial recognition Recommendation engine Cognitive Reasoning ANDMore…
  20. 20. Machine Learning How do you engineer the best features? Machinelearning 𝑁 × 𝑁 Arjun NEURAL NETWORK 𝒇 𝟏, 𝒇 𝟐, … , 𝒇 𝑲 Roundness of face Dist between eyes Nose width Eye socket depth Cheek bone structure Jaw line length …etc. CLASSIFIER ALGORITHM SVM Random Forest Naïve Bayes Decision Trees Logistic Regression Ensemble methods 𝑁 × 𝑁 Arjun DeepLearning How do you guide the model to find the best features?
  21. 21. Deeplearning:Trainingvs.inference Lots of labeled data! Training Inference Forward Backward Model weights Forward “Bicycle”? “Strawberry” “Bicycle”? Error Human Bicycle Strawberry ?????? Data set size Accuracy Didyouknow? Training requires a very large data set and deep neural network (i.e. many layers) to achieve the highest accuracy in most cases
  22. 22. AIportfolio †Beta available ‡ Future *Other names and brands may be claimed as the property of others. Tools Platforms technology Frameworks libraries END-TO-END COMPUTE SYSTEMS & COMPONENTS Intel® Deep Learning System ‡ * Solutions Data Scientists Technical Services Reference Solutions REASONING Intel® AI DevCloud ON *‡ Intel® Deep Learning Studio‡ Intel® Deep Learning Deployment Toolkit† OpenVINO™ Intel® Movidius™ Software Development Kit (SDK) * * * * *‡ *‡ *‡ ‡ DIRECT OPTIMIZATION Intel® MKL/MKL-DNN, clDNN, DAAL, Intel Python Distribution, etc. Intel® nGraph™ Library † NNP Transformer ‡ CPU Transformer † Other
  23. 23. Today DigitalSecurity&Surveillance 2018+ ScalingtoIndustrial&Retail,EnabledbySWTools OpenVINO™ 24
  24. 24. “Computer vision is concerned with the automatic extraction, analysis and understanding of useful information from a single image or a sequence of images.” Source: http://www.bmva.org/visionoverview
  25. 25. “OpenCV (Open Source Computer Vision Library) is an open source computer vision and machine learning software library.” • BSD License • More than 2500 optimized algorithms • User community with more than 47k people • Estimated 14 million downloads • C++, Python, Java and MATLAB interfaces • Supports Linux, Windows, MacOS and Android • Uses MMX and SSE instructions • Officially launched in 1999, the OpenCV project was initially an Intel Research initiative Sources: https://opencv.org/about.html and https://en.wikipedia.org/wiki/OpenCV
  26. 26. • In a nutshell: a color image is a three dimensional array (one element for each pixel, one layer for each color) Computational image manipulation is basically array-based math
  27. 27. • Open and loose definition: “an interesting part of an image” • Some OpenCV algorithms from version 2.x are patented (removed on OpenCV 3.x)
  28. 28. The complexity of the problem (data set) dictates the network structure. The more complex the problem, the more ‘features’ required, the deeper the network.
  29. 29. Traditional With OpenVINO™ Toolkit Pre-trained Models Video/Image Pre-trained Models Video/Image One-Time Process .xml, .bin User Application + Inference Engine Model Optimizer User Application + Inference
  30. 30. • Converts models from various frameworks (Intel® Optimization for Caffe*, Intel® Optimization for TensorFlow*, Apache* MXNet*) • Converts to a unified model (IR, later n-graph) • Optimizes topologies (node merging, batch normalization elimination, performing horizontal fusion) • Folds constants paths in graph
  31. 31. • Simple and unified API for inference across all Intel® architecture • Optimized inference on large Intel® architecture hardware targets (CPU/GEN/FPGA) • Heterogeneous support allows execution of layers across hardware types • Asynchronous execution improves performance • Futureproof/scale development for future Intel® architecture processors Inference Engine Common API PluginArchitecture Inference Engine Runtime Intel® Movidius™ API Intel® Movidius™ Myriad™ 2 DLA Intel Integrated Graphics (GPU) CPU: Intel® Xeon®/Intel® Core™/Intel Atom® clDNN Plugin Intel® MKL-DNN Plugin OpenCL™Intrinsics* FPGA Plugin Applications/Service Intel® Arria® 10 FPGA Intel® Movidius™ Plugin
  32. 32. • Power/Performance Efficiency Varies – Running the right workload on the right piece of hardware  higher efficiency – Hardware acceleration is a must – Heterogeneous computing? • Tradeoffs – Power/performance – Price – Software flexibility, portability PowerEfficiency Computation Flexibility Dedicated Hardware GPU CPU X1 X10 X100 Vision Processing Efficiency Vision DSPs FPGA
  33. 33. • Neural network accelerator in USB stick form factor • Tensorflow* and Caffe* and many popular frames are supported • Prototype, tune, validate, and deploy deep neural networks at the edge • Features the same Intel® Movidius™ Vision Processing Unit (VPU) used in drones, surveillance cameras, virtual reality headsets, and other low-power intelligent and autonomous products
  34. 34. Source: https://software.intel.com/en-us/distribution-for-python • Support for Python 3.6 • Performance accelerations: Scikit-learn with Intel® Data Analytics Acceleration Library (Intel® DAAL), fast Fourier transforms in SciPy and Numpy, universal functions (ufuncs) can use multiple cores and Single Instructions Multiple Data (SIMD), and neural network enhancements for pyDAAL • Stand-Alone version: Linux*, Windows* and macOS* • Conda* Packages • Docker* Images • Linux* Package Management Repositories (YUM / APT) • Support forum
  35. 35. Internet of Things Artificial Intelligence Connected & Autonomous World 36
  36. 36. 37 Demo available at: https://intel.ly/2IVUMRp Face Access Control Solution
  37. 37. 38 Internet User Interface Gateway Lock MQTT HTTP Server 1 Application Server 2 Front End MQTT Broker MQTT
  38. 38. *Other names and brands may be claimed as the property of others. 39
  39. 39. Inspiringandinvestingindevelopers 1 The total addressable market for IoT was 7.4M developers in Q2 2017, Developer Economics Q3 2017 | www.DeveloperEconomics.com & Slash Data 2 IoT devices 50 billion by 2020 representing $6 trillion invested, Technocracy News & Trends 2016, & PCMag IoTDevelopersandgrowing1 Multi-$Billionsinmarketopportunities2 7.4Million 40
  40. 40. KITS IDEs Resources Optimization Notice Copyright © 2018, Intel Corporation. All rights reserved. *Other names and brands may be claimed as the property of others. UP Squared* Grove* IoT Development Kit For Rapid Prototyping For Production & Performance Optimization Hardware Board OS Sensors Plugs-in easily into Eclipse*, Microsoft Visual Studio*, or Wind River Workbench* 150+ code samples Reference implementations Tools, Libraries, SDKs, APIs Sensor drivers SDKs Accelerate Computer Vision, Integrate Deep Learning Inference OpenVINO™ Deliver Fast, High-Density Video & Image Processing - Intel® Media SDK or Intel® Media Server Studio Customize Solutions, Optimize Compute with Intel® Graphics Intel® SDK for OpenCL* Applications FREE Special Function SDKs: software.intel.com/IoT How-to articles Documentation OS resources 41
  41. 41. Learn Develop Share  Online tutorials  Webinars  Student kits  Support forums  Intel Optimized Frameworks  Exclusive access to Intel® AI DevCloud  Project showcase opportunities at  Intel Developer Mesh  Industry & Academic events  Comprehensive courseware  Hands-on labs  Cloud compute  Technical Support Teach For developers, students, instructors and startups Intel®AIacademy software.intel.com/ai

×