IBM AI Talks #4: Adversarial Robustness 360 Toolbox For ML
•
0 likes•332 views
The 4th session of AI Trust, Bias, Explainability Series by IBM AI. Date: 8/24, 2020 10am PST Title: Adversarial Robustness 360 Toolbox For ML Website: https://learn.xnextcon.com/event/eventdetails/W20082410 Abstract: Welcome to the "AI Trust, Bias and Explainability" learning series, by IBM AI. In collaboration with IBM team, we host a series of practical introductory sessions to AI trust, bias and explainability. This is the 4th session: Adversarial samples are inputs to Machine Learning models that an adversary has tampered with in order to cause specific misclassifications. It is surprisingly easy to create adversarial samples and surprisingly difficult to defend ML models against them. This poses potential threats to the deployment of ML in security critical applications. In this webinar I will review the state-of-the-art on adversarial samples and discuss recent progress in developing ML models that are robust against adversarial samples. Most time will spent on looking how to use the Adversarial Robustness Toolbox (ART) open source project to evaluate the robustness of ML models under various types of threats. All sessions of the series: Jul 27th - AI Security Privacy-Preserving Machine Learning by IBM AI. Session 1 Aug 10th - Explainable AI Workflows using Python. Session 2 Aug 17th - Understanding and Removing Unfair Bias in ML. Session 3 Aug 24th - Adversarial Robustness 360 Toolbox For ML. Session 4 Aug 31st - Workshop: Explainable AI Workflows. Session 5
Report
Share
Report
Share
Download to read offline
Recommended
Walk Through a Real World ML Production Project
Success in productionizing ML models is difficult to achieve due to tools, processes and operational procedures. In this session, we demonstrate how data scientists and ML engineers collaborate and efficiently deploy models to production with the Wallaroo platform.
Using a real world scenario we will click down into the ML production journey that Data Scientists and ML engineers go through to take ML models into production. In this session you will learn:
The current pain points and blockers to production
The 2 persona roles in the ML production process. Data Scientist (DS) and ML Engineer
How the ML engineer creates a workspace in Wallaroo, and invites the DS to collaborate
How the DS uploads and deploys models to WL performing simple validation checks on output
How the ML Engineer can check model health (inference speed, etc)
How the DS checks logs, looks for anomalies
How the DS switches model in the pipeline
Speakers: Nina Zumel, Martin Bald
Redefining MLOps with Model Deployment, Management and Observability in Produ...
Tech talk: https://www.aicamp.ai/event/eventdetails/W2022052410
What happens after your machine learning models are deployed in production? How do you make sure that your model performance does not degrade as data and the world change?
The constantly changing data creates challenges for data scientists and engineering teams on how to detect which models have been affected and how to get their ML applications up and running seamlessly.
In this session we will take a deep dive into the new ML model monitoring and drift detection technology. We will discuss:
- How to track the ongoing accuracy of their models in production
- How to immediately detect drift before it causes significant damage to the business
- How to locate the cause of model drifting in live environments.
We will also discuss how data scientists and ML engineers can collaborate effectively using their respective tools to identify issues and take the necessary actions with a live demo and a real world use case.
Speaker: Younes Amar, Head of Product Wallaroo AI.
Resources: https://docs.wallaroo.ai/
Productizing Machine Learning at the Edge
These days, training of the Machine Learning models at the device Edge is still a risky endeavor. It is frequently considered a purely academic subject with little value for real-life product development.
In her talk, Vera will challenge this misconception, talk about the advantages of learning at the Edge and guide you through the Edge learning decision-making framework and design principles.
https://www.aicamp.ai/event/eventdetails/W2021102210
Transformers in Vision: From Zero to Hero
Attention Is All You Need.
With these simple words, the Deep Learning industry was forever changed. Transformers were initially introduced in the field of Natural Language Processing to enhance language translation, but they demonstrated astonishing results even outside language processing. In particular, they recently spread in the Computer Vision community, advancing the state-of-the-art on many vision tasks. But what are Transformers? What is the mechanism of self-attention, and do we really need it? How did they revolutionize Computer Vision? Will they ever replace convolutional neural networks?
These and many other questions will be answered during the talk.
In this tech talk, we will discuss:
- A piece of history: Why did we need a new architecture?
- What is self-attention, and where does this concept come from?
- The Transformer architecture and its mechanisms
- Vision Transformers: An Image is worth 16x16 words
- Video Understanding using Transformers: the space + time approach
- The scale and data problem: Is Attention what we really need?
- The future of Computer Vision through Transformers
Speaker: Davide Coccomini, Nicola Messina
Website: https://www.aicamp.ai/event/eventdetails/W2021101110
Deep AutoViML For Tensorflow Models and MLOps Workflows
deep_autoviml is a powerful new deep learning library with a very simple design goal: Make it as easy as possible for novices and experts alike to experiment with and build tensorflow.keras preprocessing pipelines and models in as few lines of code as possible.
deep_autoviml will enable data scientists, ML engineers and data engineers to fast prototype tensorflow models and data pipelines for MLOps workflows using the latest TF 2.4+ and keras preprocessing layers. You can now upload your saved model to any Cloud provider and make predictions out of the box since all the data preprocessing layers are attached to the model itself!
In this webinar, we will discuss the problems that deep_AutoViML can solve, its architecture design and demo how to build powerful TF.Keras models on structured data, NLP and Image data domains.
https://www.aicamp.ai/event/eventdetails/W2021080918
Metaflow: The ML Infrastructure at Netflix
Metaflow was started at Netflix to answer a pressing business need: How to enable an organization of data scientists, who are not software engineers by training, build and deploy end-to-end machine learning workflows and applications independently. We wanted to provide the best possible user experience for data scientists, allowing them to focus on parts they like (modeling using their favorite off-the-shelf libraries) while providing robust built-in solutions for the foundational infrastructure: data, compute, orchestration, and versioning.
Today, the open-source Metaflow powers hundreds of business-critical ML projects at Netflix and other companies from bioinformatics to real estate.
In this talk, you will learn about:
- What to expect from a modern ML infrastructure stack.
- Using Metaflow to boost the productivity of your data science organization, based on lessons learned from Netflix.
- Deployment strategies for a full stack of ML infrastructure that plays nicely with your existing systems and policies.
https://www.aicamp.ai/event/eventdetails/W2021080510
Practical Crowdsourcing for ML at Scale
Daria Baidakova is the Director of Educational Programs at Toloka, an open crowdsourcing platform. She manages crowdsourcing courses and organizes tutorials and hackathons. Toloka provides labeled data via crowdsourcing which is a missing pillar of AI. It offers data annotation, content collection, and business decision making through crowdsourcing. Toloka manages quality through controls at the project level, performer selection, and result aggregation rather than direct management of individuals.
Building large scale transactional data lake using apache hudi
Data is a critical infrastructure for building machine learning systems. From ensuring accurate ETAs to predicting optimal traffic routes, providing safe, seamless transportation and delivery experiences on the Uber platform requires reliable, performant large-scale data storage and analysis. In 2016, Uber developed Apache Hudi, an incremental processing framework, to power business critical data pipelines at low latency and high efficiency, and helps distributed organizations build and manage petabyte-scale data lakes.
In this talk, I will describe what is APache Hudi and its architectural design, and then deep dive to improving data operations by providing features such as data versioning, time travel.
We will also go over how Hudi brings kappa architecture to big data systems and enables efficient incremental processing for near real time use cases.
Speaker: Satish Kotha (Uber)
Apache Hudi committer and Engineer at Uber. Previously, he worked on building real time distributed storage systems like Twitter MetricsDB and BlobStore.
website: https://www.aicamp.ai/event/eventdetails/W2021043010
Recommended
Walk Through a Real World ML Production Project
Success in productionizing ML models is difficult to achieve due to tools, processes and operational procedures. In this session, we demonstrate how data scientists and ML engineers collaborate and efficiently deploy models to production with the Wallaroo platform.
Using a real world scenario we will click down into the ML production journey that Data Scientists and ML engineers go through to take ML models into production. In this session you will learn:
The current pain points and blockers to production
The 2 persona roles in the ML production process. Data Scientist (DS) and ML Engineer
How the ML engineer creates a workspace in Wallaroo, and invites the DS to collaborate
How the DS uploads and deploys models to WL performing simple validation checks on output
How the ML Engineer can check model health (inference speed, etc)
How the DS checks logs, looks for anomalies
How the DS switches model in the pipeline
Speakers: Nina Zumel, Martin Bald
Redefining MLOps with Model Deployment, Management and Observability in Produ...
Tech talk: https://www.aicamp.ai/event/eventdetails/W2022052410
What happens after your machine learning models are deployed in production? How do you make sure that your model performance does not degrade as data and the world change?
The constantly changing data creates challenges for data scientists and engineering teams on how to detect which models have been affected and how to get their ML applications up and running seamlessly.
In this session we will take a deep dive into the new ML model monitoring and drift detection technology. We will discuss:
- How to track the ongoing accuracy of their models in production
- How to immediately detect drift before it causes significant damage to the business
- How to locate the cause of model drifting in live environments.
We will also discuss how data scientists and ML engineers can collaborate effectively using their respective tools to identify issues and take the necessary actions with a live demo and a real world use case.
Speaker: Younes Amar, Head of Product Wallaroo AI.
Resources: https://docs.wallaroo.ai/
Productizing Machine Learning at the Edge
These days, training of the Machine Learning models at the device Edge is still a risky endeavor. It is frequently considered a purely academic subject with little value for real-life product development.
In her talk, Vera will challenge this misconception, talk about the advantages of learning at the Edge and guide you through the Edge learning decision-making framework and design principles.
https://www.aicamp.ai/event/eventdetails/W2021102210
Transformers in Vision: From Zero to Hero
Attention Is All You Need.
With these simple words, the Deep Learning industry was forever changed. Transformers were initially introduced in the field of Natural Language Processing to enhance language translation, but they demonstrated astonishing results even outside language processing. In particular, they recently spread in the Computer Vision community, advancing the state-of-the-art on many vision tasks. But what are Transformers? What is the mechanism of self-attention, and do we really need it? How did they revolutionize Computer Vision? Will they ever replace convolutional neural networks?
These and many other questions will be answered during the talk.
In this tech talk, we will discuss:
- A piece of history: Why did we need a new architecture?
- What is self-attention, and where does this concept come from?
- The Transformer architecture and its mechanisms
- Vision Transformers: An Image is worth 16x16 words
- Video Understanding using Transformers: the space + time approach
- The scale and data problem: Is Attention what we really need?
- The future of Computer Vision through Transformers
Speaker: Davide Coccomini, Nicola Messina
Website: https://www.aicamp.ai/event/eventdetails/W2021101110
Deep AutoViML For Tensorflow Models and MLOps Workflows
deep_autoviml is a powerful new deep learning library with a very simple design goal: Make it as easy as possible for novices and experts alike to experiment with and build tensorflow.keras preprocessing pipelines and models in as few lines of code as possible.
deep_autoviml will enable data scientists, ML engineers and data engineers to fast prototype tensorflow models and data pipelines for MLOps workflows using the latest TF 2.4+ and keras preprocessing layers. You can now upload your saved model to any Cloud provider and make predictions out of the box since all the data preprocessing layers are attached to the model itself!
In this webinar, we will discuss the problems that deep_AutoViML can solve, its architecture design and demo how to build powerful TF.Keras models on structured data, NLP and Image data domains.
https://www.aicamp.ai/event/eventdetails/W2021080918
Metaflow: The ML Infrastructure at Netflix
Metaflow was started at Netflix to answer a pressing business need: How to enable an organization of data scientists, who are not software engineers by training, build and deploy end-to-end machine learning workflows and applications independently. We wanted to provide the best possible user experience for data scientists, allowing them to focus on parts they like (modeling using their favorite off-the-shelf libraries) while providing robust built-in solutions for the foundational infrastructure: data, compute, orchestration, and versioning.
Today, the open-source Metaflow powers hundreds of business-critical ML projects at Netflix and other companies from bioinformatics to real estate.
In this talk, you will learn about:
- What to expect from a modern ML infrastructure stack.
- Using Metaflow to boost the productivity of your data science organization, based on lessons learned from Netflix.
- Deployment strategies for a full stack of ML infrastructure that plays nicely with your existing systems and policies.
https://www.aicamp.ai/event/eventdetails/W2021080510
Practical Crowdsourcing for ML at Scale
Daria Baidakova is the Director of Educational Programs at Toloka, an open crowdsourcing platform. She manages crowdsourcing courses and organizes tutorials and hackathons. Toloka provides labeled data via crowdsourcing which is a missing pillar of AI. It offers data annotation, content collection, and business decision making through crowdsourcing. Toloka manages quality through controls at the project level, performer selection, and result aggregation rather than direct management of individuals.
Building large scale transactional data lake using apache hudi
Data is a critical infrastructure for building machine learning systems. From ensuring accurate ETAs to predicting optimal traffic routes, providing safe, seamless transportation and delivery experiences on the Uber platform requires reliable, performant large-scale data storage and analysis. In 2016, Uber developed Apache Hudi, an incremental processing framework, to power business critical data pipelines at low latency and high efficiency, and helps distributed organizations build and manage petabyte-scale data lakes.
In this talk, I will describe what is APache Hudi and its architectural design, and then deep dive to improving data operations by providing features such as data versioning, time travel.
We will also go over how Hudi brings kappa architecture to big data systems and enables efficient incremental processing for near real time use cases.
Speaker: Satish Kotha (Uber)
Apache Hudi committer and Engineer at Uber. Previously, he worked on building real time distributed storage systems like Twitter MetricsDB and BlobStore.
website: https://www.aicamp.ai/event/eventdetails/W2021043010
Deep Reinforcement Learning and Its Applications
What is the most exciting AI news in recent years? AlphaGo!
What are key techniques for AlphaGo? Deep learning and reinforcement learning (RL)!
What are application areas for deep RL? A lot! In fact, besides games, deep RL has been making tremendous achievements in diverse areas like recommender systems and robotics.
In this talk, we will introduce deep reinforcement learning, present several applications, and discuss issues and potential solutions for successfully applying deep RL in real life scenarios.
https://www.aicamp.ai/event/eventdetails/W2021042818
Big Data and AI in Fighting Against COVID-19
This document discusses how big data and AI can help fight Covid-19. It describes supercomputers being used for scientific research on Covid-19. An open data lake has been created containing various Covid-19 datasets for analysis. Natural language processing and BERT are being used to answer scientific questions from the Covid-19 literature by generating summaries and highlighting relevant text passages. Challenges are being conducted on the Covid-19 Open Research Dataset to further advance research.
Highly-scalable Reinforcement Learning RLlib for Real-world Applications
This document discusses Ray and RLlib, a reinforcement learning library built on Ray. It provides three key points:
1. Ray is a framework for building distributed applications and services with shared memory abstraction. It allows ML workloads to scale beyond a single machine.
2. RLlib is a scalable reinforcement learning library that uses Ray. It supports a wide range of algorithms and execution models. This allows for easy implementation and comparison of RL techniques.
3. The Ray community is growing rapidly and provides resources like tutorials and Slack support to help users adopt Ray and RLlib for their distributed Python and reinforcement learning applications.
Build computer vision models to perform object detection and classification w...
event: https://learn.xnextcon.com/event/eventdetails/W20042918
video:
description: Computer Vision has received significant attention over the recent years, both within academia, and industry. As the state-of-the-art rapidly improves, the art-of-the-possible follows , offering innovative forms of computer vision applications for different scenarios.
In this talk, Ramine will cover the background and development of computer vision, and demonstrate how to use AWS to build robust, computer vision models to perform object detection and classification.
Key Takeaways:
Understand the history of Computer Vision
Learn how to use Amazon SageMaker to build and Deploy Computer Vision Models
How to orchestrate multiple models for implementing a real-world use case
Causal Inference in Data Science and Machine Learning
Event: https://learn.xnextcon.com/event/eventdetails/W20042010
Video: https://www.youtube.com/channel/UCj09XsAWj-RF9kY4UvBJh_A
Modern machine learning techniques are able to learn highly complex associations from data, which has led to amazing progress in computer vision, NLP, and other predictive tasks. However, there are limitations to inference from purely probabilistic or associational information. Without understanding causal relationships, ML models are unable to provide actionable recommendations, perform poorly in new, but related environments, and suffer from a lack of interpretability.
In this talk, I provide an introduction to the field of causal inference, discuss its importance in addressing some of the current limitations in machine learning, and provide some real-world examples from my experience as a data scientist at Brex.
Weekly #106: Deep Learning on Mobile
https://learn.xnextcon.com/event/eventdetails/W20040610
This talk explains how to practically bring the power of convolutional neural networks and deep learning to memory and power-constrained devices like smartphones. You will learn various strategies to circumvent obstacles and build mobile-friendly shallow CNN architectures that significantly reduce the memory footprint and therefore make them easier to store on a smartphone;
The talk also dives into how to use a family of model compression techniques to prune the network size for live image processing, enabling you to build a CNN version optimized for inference on mobile devices. Along the way, you will learn practical strategies to preprocess your data in a manner that makes the models more efficient in the real world.
Weekly #105: AutoViz and Auto_ViML Visualization and Machine Learning
https://learn.xnextcon.com/event/eventdetails/W20040310
I will describe what is available in terms of Open Source and Proprietary tools for automating Data Science tasks and introduce 2 new tools: one to visualize any sized data set with one click, another: to try multiple ML models and techniques with a single call. I will provide the Github Repos for both for free in the talk.
AISF19 - On Blending Machine Learning with Microeconomics
The document discusses how machine learning and economics can inform each other. It describes how markets can be viewed as decentralized algorithms that solve complex tasks. Recommendation systems are discussed as an example of machine learning success, but it is noted that recommending the same items to everyone is problematic. As an alternative, the document proposes creating markets with recommendation systems on both sides, like a market connecting diners and restaurants. The rest of the document discusses several specific examples at the intersection of machine learning and economics research, like bandits that compete and finding Nash equilibria with gradient-based algorithms.
AISF19 - Travel in the AI-First World
Travel is a force for good economically and socially. Expedia Group is building towards an "AI-First World" of travel where AI is used throughout the entire travel planning, booking, and experience process. They are developing massive multi-dimensional AI models and an AI platform to deliver highly personalized and targeted experiences. Overcoming challenges like data quality, scalability, and control will be key to realizing an AI-First vision where travel is optimized for each individual user.
AISF19 - Unleash Computer Vision at the Edge
This document discusses the key drivers enabling computer vision at the edge, including new machine learning approaches, optimized model architectures, hardware innovations, and improved software tools. It describes how machine learning has advanced computer vision by enabling end-to-end learning without predefined features. Edge-optimized models like GoogleNet and ShuffleNet are discussed. The proliferation of cameras, embedded processors, and AI accelerators is enabling computer vision everywhere. Open-source tools like OpenCV and frameworks like TensorFlow are supporting development, along with platforms to speed application creation.
AISF19 - Building Scalable, Kubernetes-Native ML/AI Pipelines with TFX, KubeF...
This document discusses modern machine learning pipelines and popular open source tools to build them. It defines key characteristics of ML pipelines like experiment tracking, hyperparameter optimization, distributed execution, and metadata/data versioning. Popular tools covered are KubeFlow for Kubernetes+TensorFlow, Airflow for data and feature engineering, MLflow for experiment tracking, and TensorFlow Extended (TFX) libraries. The document demonstrates these tools and argues that while the field is emerging, simplicity is important and one should only use necessary components of different tools.
Toronto meetup 20190917
This document discusses elastic distributed deep learning training at scale on-premises and in the cloud. It introduces the architecture of elastic distributed training, which combines high performance synchronization techniques like distributed data parallel with session scheduling and elastic scaling to provide flexibility. This allows training jobs to automatically scale up and down resources based on policies while maintaining high performance. It aims to make distributed training transparent to frameworks like TensorFlow and PyTorch.
Feature Engineering for NLP
Monthly AI Tech Talks in Toronto 2019-08-28
https://www.meetup.com/aittg-toronto
The talk will cover the end-to-end details including contextual and linguistic feature extraction, vectorization, n-grams, topic modeling, named entity resolution which are based on concepts from mathematics, information retrieval and natural language processing. We will also be diving into more advanced feature engineering strategies such as word2vec, GloVe and fastText that leverage deep learning models.
In addition, attendees will learn how to combine NLP features with numeric and categorical features and analyze the feature importance from the resulting models.
The following libraries will be used to demonstrate the aforementioned feature engineering techniques: spaCy, Gensim, fasText and Keras in Python.
https://www.meetup.com/aittg-toronto/events/261940480/
Auto visualization and viml
http://ainyc19.xnextcon.com
I will describe what is available in terms of Open Source and Proprietary tools for automating Data Science tasks and introduce 2 new tools: one to visualize any sized data set with one click, another: to try multiple ML models and techniques with a single call. I will provide the Github Repos for both for free in the talk.
Explainability and bias in AI
The document discusses explainability and bias in machine learning/AI models. It covers several topics:
1. Why explainability of models is important, including for laypeople using models and potential legal needs for explanations of decisions.
2. Methods for explainability including using interpretable models directly and post-hoc explainability methods like LIME and SHAP which provide feature attributions.
3. Issues with bias in machine learning models and different definitions of fairness. It also discusses techniques for measuring and mitigating bias, such as reweighting data or using adversarial learning.
An Introduction to Neural Architecture Search
https://learn.xnextcon.com/event/eventdetails/W19071910
video: https://www.youtube.com/channel/UCj09XsAWj-RF9kY4UvBJh_A
photos: flickr.com/photos/nextcon/albums
weekly AI tech talk #85 ml-agents Enabling Learned Behaviors with Reinforceme...
https://learn.xnextcon.com/event/eventdetails/W19061910
Behaviors in games---and in the real world---are often difficult to program explicitly. Reinforcement learning (RL) has shown success in learning behaviors based on a simple defined reward function that incentivises correct behavior.
Unity ML-Agents toolkit enables Unity developers to train reinforcement learning models to control behaviors within their games. Once these models are trained, they can be integrated across platforms into a game build via the Unity Inference Engine.
Furthermore, by enabling communication between a Unity build and Python code, ML-Agents enables RL researchers to use Unity games as training environments.
Data stream with cruise control
The document discusses Cruise Control, a tool for managing Apache Kafka clusters. It was created by LinkedIn to handle their large Kafka deployment consisting of over 2,000 brokers and 4 trillion messages per day. Cruise Control monitors broker loads, detects anomalies, and generates proposals to optimize resource usage and replica distributions. It supports operations like adding or removing brokers and performing automatic rebalances without downtime or data loss. The architecture includes components for load monitoring, analysis, execution and an API for administration.
AI in linkedin
AI to create professional opportunities
Liang Zhang discussed how AI is used at LinkedIn to create opportunities. LinkedIn uses AI throughout its platform including in personalized recommendations, search, and video. It processes vast amounts of data using machine learning models to tailor experiences for each user. Zhang outlined LinkedIn's approach to personalization at scale using global, per-user, and per-item models.
Deep natural language processing in search systems
This document discusses applying deep natural language processing techniques to various components of search systems, including query understanding, document ranking, auto-completion, and query suggestion. It describes challenges like data ambiguity, deep semantics, and online latency constraints. Several deep learning models are explored, like CNNs, LSTMs, CRFs, and BERT, for tasks like query tagging, intent classification, and neural ranking. Both offline and online experiments show potential gains from these techniques.
What is an RPA CoE? Session 2 – CoE Roles
In this session, we will review the players involved in the CoE and how each role impacts opportunities.
Topics covered:
• What roles are essential?
• What place in the automation journey does each role play?
Speaker:
Chris Bolin, Senior Intelligent Automation Architect Anika Systems
Astute Business Solutions | Oracle Cloud Partner |
Your goto partner for Oracle Cloud, PeopleSoft, E-Business Suite, and Ellucian Banner. We are a firm specialized in managed services and consulting.
More Related Content
More from Bill Liu
Deep Reinforcement Learning and Its Applications
What is the most exciting AI news in recent years? AlphaGo!
What are key techniques for AlphaGo? Deep learning and reinforcement learning (RL)!
What are application areas for deep RL? A lot! In fact, besides games, deep RL has been making tremendous achievements in diverse areas like recommender systems and robotics.
In this talk, we will introduce deep reinforcement learning, present several applications, and discuss issues and potential solutions for successfully applying deep RL in real life scenarios.
https://www.aicamp.ai/event/eventdetails/W2021042818
Big Data and AI in Fighting Against COVID-19
This document discusses how big data and AI can help fight Covid-19. It describes supercomputers being used for scientific research on Covid-19. An open data lake has been created containing various Covid-19 datasets for analysis. Natural language processing and BERT are being used to answer scientific questions from the Covid-19 literature by generating summaries and highlighting relevant text passages. Challenges are being conducted on the Covid-19 Open Research Dataset to further advance research.
Highly-scalable Reinforcement Learning RLlib for Real-world Applications
This document discusses Ray and RLlib, a reinforcement learning library built on Ray. It provides three key points:
1. Ray is a framework for building distributed applications and services with shared memory abstraction. It allows ML workloads to scale beyond a single machine.
2. RLlib is a scalable reinforcement learning library that uses Ray. It supports a wide range of algorithms and execution models. This allows for easy implementation and comparison of RL techniques.
3. The Ray community is growing rapidly and provides resources like tutorials and Slack support to help users adopt Ray and RLlib for their distributed Python and reinforcement learning applications.
Build computer vision models to perform object detection and classification w...
event: https://learn.xnextcon.com/event/eventdetails/W20042918
video:
description: Computer Vision has received significant attention over the recent years, both within academia, and industry. As the state-of-the-art rapidly improves, the art-of-the-possible follows , offering innovative forms of computer vision applications for different scenarios.
In this talk, Ramine will cover the background and development of computer vision, and demonstrate how to use AWS to build robust, computer vision models to perform object detection and classification.
Key Takeaways:
Understand the history of Computer Vision
Learn how to use Amazon SageMaker to build and Deploy Computer Vision Models
How to orchestrate multiple models for implementing a real-world use case
Causal Inference in Data Science and Machine Learning
Event: https://learn.xnextcon.com/event/eventdetails/W20042010
Video: https://www.youtube.com/channel/UCj09XsAWj-RF9kY4UvBJh_A
Modern machine learning techniques are able to learn highly complex associations from data, which has led to amazing progress in computer vision, NLP, and other predictive tasks. However, there are limitations to inference from purely probabilistic or associational information. Without understanding causal relationships, ML models are unable to provide actionable recommendations, perform poorly in new, but related environments, and suffer from a lack of interpretability.
In this talk, I provide an introduction to the field of causal inference, discuss its importance in addressing some of the current limitations in machine learning, and provide some real-world examples from my experience as a data scientist at Brex.
Weekly #106: Deep Learning on Mobile
https://learn.xnextcon.com/event/eventdetails/W20040610
This talk explains how to practically bring the power of convolutional neural networks and deep learning to memory and power-constrained devices like smartphones. You will learn various strategies to circumvent obstacles and build mobile-friendly shallow CNN architectures that significantly reduce the memory footprint and therefore make them easier to store on a smartphone;
The talk also dives into how to use a family of model compression techniques to prune the network size for live image processing, enabling you to build a CNN version optimized for inference on mobile devices. Along the way, you will learn practical strategies to preprocess your data in a manner that makes the models more efficient in the real world.
Weekly #105: AutoViz and Auto_ViML Visualization and Machine Learning
https://learn.xnextcon.com/event/eventdetails/W20040310
I will describe what is available in terms of Open Source and Proprietary tools for automating Data Science tasks and introduce 2 new tools: one to visualize any sized data set with one click, another: to try multiple ML models and techniques with a single call. I will provide the Github Repos for both for free in the talk.
AISF19 - On Blending Machine Learning with Microeconomics
The document discusses how machine learning and economics can inform each other. It describes how markets can be viewed as decentralized algorithms that solve complex tasks. Recommendation systems are discussed as an example of machine learning success, but it is noted that recommending the same items to everyone is problematic. As an alternative, the document proposes creating markets with recommendation systems on both sides, like a market connecting diners and restaurants. The rest of the document discusses several specific examples at the intersection of machine learning and economics research, like bandits that compete and finding Nash equilibria with gradient-based algorithms.
AISF19 - Travel in the AI-First World
Travel is a force for good economically and socially. Expedia Group is building towards an "AI-First World" of travel where AI is used throughout the entire travel planning, booking, and experience process. They are developing massive multi-dimensional AI models and an AI platform to deliver highly personalized and targeted experiences. Overcoming challenges like data quality, scalability, and control will be key to realizing an AI-First vision where travel is optimized for each individual user.
AISF19 - Unleash Computer Vision at the Edge
This document discusses the key drivers enabling computer vision at the edge, including new machine learning approaches, optimized model architectures, hardware innovations, and improved software tools. It describes how machine learning has advanced computer vision by enabling end-to-end learning without predefined features. Edge-optimized models like GoogleNet and ShuffleNet are discussed. The proliferation of cameras, embedded processors, and AI accelerators is enabling computer vision everywhere. Open-source tools like OpenCV and frameworks like TensorFlow are supporting development, along with platforms to speed application creation.
AISF19 - Building Scalable, Kubernetes-Native ML/AI Pipelines with TFX, KubeF...
This document discusses modern machine learning pipelines and popular open source tools to build them. It defines key characteristics of ML pipelines like experiment tracking, hyperparameter optimization, distributed execution, and metadata/data versioning. Popular tools covered are KubeFlow for Kubernetes+TensorFlow, Airflow for data and feature engineering, MLflow for experiment tracking, and TensorFlow Extended (TFX) libraries. The document demonstrates these tools and argues that while the field is emerging, simplicity is important and one should only use necessary components of different tools.
Toronto meetup 20190917
This document discusses elastic distributed deep learning training at scale on-premises and in the cloud. It introduces the architecture of elastic distributed training, which combines high performance synchronization techniques like distributed data parallel with session scheduling and elastic scaling to provide flexibility. This allows training jobs to automatically scale up and down resources based on policies while maintaining high performance. It aims to make distributed training transparent to frameworks like TensorFlow and PyTorch.
Feature Engineering for NLP
Monthly AI Tech Talks in Toronto 2019-08-28
https://www.meetup.com/aittg-toronto
The talk will cover the end-to-end details including contextual and linguistic feature extraction, vectorization, n-grams, topic modeling, named entity resolution which are based on concepts from mathematics, information retrieval and natural language processing. We will also be diving into more advanced feature engineering strategies such as word2vec, GloVe and fastText that leverage deep learning models.
In addition, attendees will learn how to combine NLP features with numeric and categorical features and analyze the feature importance from the resulting models.
The following libraries will be used to demonstrate the aforementioned feature engineering techniques: spaCy, Gensim, fasText and Keras in Python.
https://www.meetup.com/aittg-toronto/events/261940480/
Auto visualization and viml
http://ainyc19.xnextcon.com
I will describe what is available in terms of Open Source and Proprietary tools for automating Data Science tasks and introduce 2 new tools: one to visualize any sized data set with one click, another: to try multiple ML models and techniques with a single call. I will provide the Github Repos for both for free in the talk.
Explainability and bias in AI
The document discusses explainability and bias in machine learning/AI models. It covers several topics:
1. Why explainability of models is important, including for laypeople using models and potential legal needs for explanations of decisions.
2. Methods for explainability including using interpretable models directly and post-hoc explainability methods like LIME and SHAP which provide feature attributions.
3. Issues with bias in machine learning models and different definitions of fairness. It also discusses techniques for measuring and mitigating bias, such as reweighting data or using adversarial learning.
An Introduction to Neural Architecture Search
https://learn.xnextcon.com/event/eventdetails/W19071910
video: https://www.youtube.com/channel/UCj09XsAWj-RF9kY4UvBJh_A
photos: flickr.com/photos/nextcon/albums
weekly AI tech talk #85 ml-agents Enabling Learned Behaviors with Reinforceme...
https://learn.xnextcon.com/event/eventdetails/W19061910
Behaviors in games---and in the real world---are often difficult to program explicitly. Reinforcement learning (RL) has shown success in learning behaviors based on a simple defined reward function that incentivises correct behavior.
Unity ML-Agents toolkit enables Unity developers to train reinforcement learning models to control behaviors within their games. Once these models are trained, they can be integrated across platforms into a game build via the Unity Inference Engine.
Furthermore, by enabling communication between a Unity build and Python code, ML-Agents enables RL researchers to use Unity games as training environments.
Data stream with cruise control
The document discusses Cruise Control, a tool for managing Apache Kafka clusters. It was created by LinkedIn to handle their large Kafka deployment consisting of over 2,000 brokers and 4 trillion messages per day. Cruise Control monitors broker loads, detects anomalies, and generates proposals to optimize resource usage and replica distributions. It supports operations like adding or removing brokers and performing automatic rebalances without downtime or data loss. The architecture includes components for load monitoring, analysis, execution and an API for administration.
AI in linkedin
AI to create professional opportunities
Liang Zhang discussed how AI is used at LinkedIn to create opportunities. LinkedIn uses AI throughout its platform including in personalized recommendations, search, and video. It processes vast amounts of data using machine learning models to tailor experiences for each user. Zhang outlined LinkedIn's approach to personalization at scale using global, per-user, and per-item models.
Deep natural language processing in search systems
This document discusses applying deep natural language processing techniques to various components of search systems, including query understanding, document ranking, auto-completion, and query suggestion. It describes challenges like data ambiguity, deep semantics, and online latency constraints. Several deep learning models are explored, like CNNs, LSTMs, CRFs, and BERT, for tasks like query tagging, intent classification, and neural ranking. Both offline and online experiments show potential gains from these techniques.
More from Bill Liu (20)
Highly-scalable Reinforcement Learning RLlib for Real-world Applications
Highly-scalable Reinforcement Learning RLlib for Real-world Applications
Build computer vision models to perform object detection and classification w...
Build computer vision models to perform object detection and classification w...
Causal Inference in Data Science and Machine Learning
Causal Inference in Data Science and Machine Learning
Weekly #105: AutoViz and Auto_ViML Visualization and Machine Learning
Weekly #105: AutoViz and Auto_ViML Visualization and Machine Learning
AISF19 - On Blending Machine Learning with Microeconomics
AISF19 - On Blending Machine Learning with Microeconomics
AISF19 - Building Scalable, Kubernetes-Native ML/AI Pipelines with TFX, KubeF...
AISF19 - Building Scalable, Kubernetes-Native ML/AI Pipelines with TFX, KubeF...
weekly AI tech talk #85 ml-agents Enabling Learned Behaviors with Reinforceme...
weekly AI tech talk #85 ml-agents Enabling Learned Behaviors with Reinforceme...
Deep natural language processing in search systems
Deep natural language processing in search systems
Recently uploaded
What is an RPA CoE? Session 2 – CoE Roles
In this session, we will review the players involved in the CoE and how each role impacts opportunities.
Topics covered:
• What roles are essential?
• What place in the automation journey does each role play?
Speaker:
Chris Bolin, Senior Intelligent Automation Architect Anika Systems
Astute Business Solutions | Oracle Cloud Partner |
Your goto partner for Oracle Cloud, PeopleSoft, E-Business Suite, and Ellucian Banner. We are a firm specialized in managed services and consulting.
Getting the Most Out of ScyllaDB Monitoring: ShareChat's Tips
ScyllaDB monitoring provides a lot of useful information. But sometimes it’s not easy to find the root of the problem if something is wrong or even estimate the remaining capacity by the load on the cluster. This talk shares our team's practical tips on: 1) How to find the root of the problem by metrics if ScyllaDB is slow 2) How to interpret the load and plan capacity for the future 3) Compaction strategies and how to choose the right one 4) Important metrics which aren’t available in the default monitoring setup.
Northern Engraving | Modern Metal Trim, Nameplates and Appliance Panels
What began over 115 years ago as a supplier of precision gauges to the automotive industry has evolved into being an industry leader in the manufacture of product branding, automotive cockpit trim and decorative appliance trim. Value-added services include in-house Design, Engineering, Program Management, Test Lab and Tool Shops.
"Scaling RAG Applications to serve millions of users", Kevin Goedecke
How we managed to grow and scale a RAG application from zero to thousands of users in 7 months. Lessons from technical challenges around managing high load for LLMs, RAGs and Vector databases.
QR Secure: A Hybrid Approach Using Machine Learning and Security Validation F...
QR Secure: A Hybrid Approach Using Machine Learning and Security Validation Functions to Prevent Interaction with Malicious QR Codes.
Aim of the Study: The goal of this research was to develop a robust hybrid approach for identifying malicious and insecure URLs derived from QR codes, ensuring safe interactions.
This is achieved through:
Machine Learning Model: Predicts the likelihood of a URL being malicious.
Security Validation Functions: Ensures the derived URL has a valid certificate and proper URL format.
This innovative blend of technology aims to enhance cybersecurity measures and protect users from potential threats hidden within QR codes 🖥 🔒
This study was my first introduction to using ML which has shown me the immense potential of ML in creating more secure digital environments!
Mutation Testing for Task-Oriented Chatbots
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.
AppSec PNW: Android and iOS Application Security with MobSF
Mobile Security Framework - MobSF is a free and open source automated mobile application security testing environment designed to help security engineers, researchers, developers, and penetration testers to identify security vulnerabilities, malicious behaviours and privacy concerns in mobile applications using static and dynamic analysis. It supports all the popular mobile application binaries and source code formats built for Android and iOS devices. In addition to automated security assessment, it also offers an interactive testing environment to build and execute scenario based test/fuzz cases against the application.
This talk covers:
Using MobSF for static analysis of mobile applications.
Interactive dynamic security assessment of Android and iOS applications.
Solving Mobile app CTF challenges.
Reverse engineering and runtime analysis of Mobile malware.
How to shift left and integrate MobSF/mobsfscan SAST and DAST in your build pipeline.
"$10 thousand per minute of downtime: architecture, queues, streaming and fin...
Direct losses from downtime in 1 minute = $5-$10 thousand dollars. Reputation is priceless.
As part of the talk, we will consider the architectural strategies necessary for the development of highly loaded fintech solutions. We will focus on using queues and streaming to efficiently work and manage large amounts of data in real-time and to minimize latency.
We will focus special attention on the architectural patterns used in the design of the fintech system, microservices and event-driven architecture, which ensure scalability, fault tolerance, and consistency of the entire system.
Day 2 - Intro to UiPath Studio Fundamentals
In our second session, we shall learn all about the main features and fundamentals of UiPath Studio that enable us to use the building blocks for any automation project.
📕 Detailed agenda:
Variables and Datatypes
Workflow Layouts
Arguments
Control Flows and Loops
Conditional Statements
💻 Extra training through UiPath Academy:
Variables, Constants, and Arguments in Studio
Control Flow in Studio
"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk
At this talk we will discuss DDoS protection tools and best practices, discuss network architectures and what AWS has to offer. Also, we will look into one of the largest DDoS attacks on Ukrainian infrastructure that happened in February 2022. We'll see, what techniques helped to keep the web resources available for Ukrainians and how AWS improved DDoS protection for all customers based on Ukraine experience
What is an RPA CoE? Session 1 – CoE Vision
In the first session, we will review the organization's vision and how this has an impact on the COE Structure.
Topics covered:
• The role of a steering committee
• How do the organization’s priorities determine CoE Structure?
Speaker:
Chris Bolin, Senior Intelligent Automation Architect Anika Systems
Dandelion Hashtable: beyond billion requests per second on a commodity server
This slide deck presents DLHT, a concurrent in-memory hashtable. Despite efforts to optimize hashtables, that go as far as sacrificing core functionality, state-of-the-art designs still incur multiple memory accesses per request and block request processing in three cases. First, most hashtables block while waiting for data to be retrieved from memory. Second, open-addressing designs, which represent the current state-of-the-art, either cannot free index slots on deletes or must block all requests to do so. Third, index resizes block every request until all objects are copied to the new index. Defying folklore wisdom, DLHT forgoes open-addressing and adopts a fully-featured and memory-aware closed-addressing design based on bounded cache-line-chaining. This design offers lock-free index operations and deletes that free slots instantly, (2) completes most requests with a single memory access, (3) utilizes software prefetching to hide memory latencies, and (4) employs a novel non-blocking and parallel resizing. In a commodity server and a memory-resident workload, DLHT surpasses 1.6B requests per second and provides 3.5x (12x) the throughput of the state-of-the-art closed-addressing (open-addressing) resizable hashtable on Gets (Deletes).
The Microsoft 365 Migration Tutorial For Beginner.pptx
This presentation will help you understand the power of Microsoft 365. However, we have mentioned every productivity app included in Office 365. Additionally, we have suggested the migration situation related to Office 365 and how we can help you.
You can also read: https://www.systoolsgroup.com/updates/office-365-tenant-to-tenant-migration-step-by-step-complete-guide/
Lee Barnes - Path to Becoming an Effective Test Automation Engineer.pdf
So… you want to become a Test Automation Engineer (or hire and develop one)? While there’s quite a bit of information available about important technical and tool skills to master, there’s not enough discussion around the path to becoming an effective Test Automation Engineer that knows how to add VALUE. In my experience this had led to a proliferation of engineers who are proficient with tools and building frameworks but have skill and knowledge gaps, especially in software testing, that reduce the value they deliver with test automation.
In this talk, Lee will share his lessons learned from over 30 years of working with, and mentoring, hundreds of Test Automation Engineers. Whether you’re looking to get started in test automation or just want to improve your trade, this talk will give you a solid foundation and roadmap for ensuring your test automation efforts continuously add value. This talk is equally valuable for both aspiring Test Automation Engineers and those managing them! All attendees will take away a set of key foundational knowledge and a high-level learning path for leveling up test automation skills and ensuring they add value to their organizations.
MySQL InnoDB Storage Engine: Deep Dive - Mydbops
This presentation, titled "MySQL - InnoDB" and delivered by Mayank Prasad at the Mydbops Open Source Database Meetup 16 on June 8th, 2024, covers dynamic configuration of REDO logs and instant ADD/DROP columns in InnoDB.
This presentation dives deep into the world of InnoDB, exploring two ground-breaking features introduced in MySQL 8.0:
• Dynamic Configuration of REDO Logs: Enhance your database's performance and flexibility with on-the-fly adjustments to REDO log capacity. Unleash the power of the snake metaphor to visualize how InnoDB manages REDO log files.
• Instant ADD/DROP Columns: Say goodbye to costly table rebuilds! This presentation unveils how InnoDB now enables seamless addition and removal of columns without compromising data integrity or incurring downtime.
Key Learnings:
• Grasp the concept of REDO logs and their significance in InnoDB's transaction management.
• Discover the advantages of dynamic REDO log configuration and how to leverage it for optimal performance.
• Understand the inner workings of instant ADD/DROP columns and their impact on database operations.
• Gain valuable insights into the row versioning mechanism that empowers instant column modifications.
Introducing BoxLang : A new JVM language for productivity and modularity!
Just like life, our code must adapt to the ever changing world we live in. From one day coding for the web, to the next for our tablets or APIs or for running serverless applications. Multi-runtime development is the future of coding, the future is to be dynamic. Let us introduce you to BoxLang.
Dynamic. Modular. Productive.
BoxLang redefines development with its dynamic nature, empowering developers to craft expressive and functional code effortlessly. Its modular architecture prioritizes flexibility, allowing for seamless integration into existing ecosystems.
Interoperability at its Core
With 100% interoperability with Java, BoxLang seamlessly bridges the gap between traditional and modern development paradigms, unlocking new possibilities for innovation and collaboration.
Multi-Runtime
From the tiny 2m operating system binary to running on our pure Java web server, CommandBox, Jakarta EE, AWS Lambda, Microsoft Functions, Web Assembly, Android and more. BoxLang has been designed to enhance and adapt according to it's runnable runtime.
The Fusion of Modernity and Tradition
Experience the fusion of modern features inspired by CFML, Node, Ruby, Kotlin, Java, and Clojure, combined with the familiarity of Java bytecode compilation, making BoxLang a language of choice for forward-thinking developers.
Empowering Transition with Transpiler Support
Transitioning from CFML to BoxLang is seamless with our JIT transpiler, facilitating smooth migration and preserving existing code investments.
Unlocking Creativity with IDE Tools
Unleash your creativity with powerful IDE tools tailored for BoxLang, providing an intuitive development experience and streamlining your workflow. Join us as we embark on a journey to redefine JVM development. Welcome to the era of BoxLang.
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
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
Recently uploaded (20)
Astute Business Solutions | Oracle Cloud Partner |
Astute Business Solutions | Oracle Cloud Partner |
Getting the Most Out of ScyllaDB Monitoring: ShareChat's Tips
Getting the Most Out of ScyllaDB Monitoring: ShareChat's Tips
Northern Engraving | Modern Metal Trim, Nameplates and Appliance Panels
Northern Engraving | Modern Metal Trim, Nameplates and Appliance Panels
"Scaling RAG Applications to serve millions of users", Kevin Goedecke
"Scaling RAG Applications to serve millions of users", Kevin Goedecke
QR Secure: A Hybrid Approach Using Machine Learning and Security Validation F...
QR Secure: A Hybrid Approach Using Machine Learning and Security Validation F...
AppSec PNW: Android and iOS Application Security with MobSF
AppSec PNW: Android and iOS Application Security with MobSF
"$10 thousand per minute of downtime: architecture, queues, streaming and fin...
"$10 thousand per minute of downtime: architecture, queues, streaming and fin...
"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk
"Frontline Battles with DDoS: Best practices and Lessons Learned", Igor Ivaniuk
Dandelion Hashtable: beyond billion requests per second on a commodity server
Dandelion Hashtable: beyond billion requests per second on a commodity server
The Microsoft 365 Migration Tutorial For Beginner.pptx
The Microsoft 365 Migration Tutorial For Beginner.pptx
Lee Barnes - Path to Becoming an Effective Test Automation Engineer.pdf
Lee Barnes - Path to Becoming an Effective Test Automation Engineer.pdf
Poznań ACE event - 19.06.2024 Team 24 Wrapup slidedeck
Poznań ACE event - 19.06.2024 Team 24 Wrapup slidedeck
Introducing BoxLang : A new JVM language for productivity and modularity!
Introducing BoxLang : A new JVM language for productivity and modularity!
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
Connector Corner: Seamlessly power UiPath Apps, GenAI with prebuilt connectors
IBM AI Talks #4: Adversarial Robustness 360 Toolbox For ML
- 1. 1 The Adversarial Robustness Toolbox Mathieu Sinn, PhD Manager AI, Security & Privacy IBM Research Europe Dublin, Ireland AICamp IBM Series on AI Trust August 24, 2020
- 2. Outline • Adversarial threats to AI • The Adversarial Robustness Toolbox • Resources & Conclusions
- 3. “AI is the new electricity”
- 4. But… AI is also surprisingly brittle! https://art-demo.mybluemix.net/
- 5. This does not only apply to images… “Basketball throw” (72.5%) “Tennis swing” (49.5%) Original Adversarial https://github.com/Trusted-AI/adversarial-robustness- toolbox/blob/main/notebooks/adversarial_action_recognition.ipynb
- 6. Adversarial Threats to AI
- 7. Financial services: • Evade fraud detection Autonomous vehicles: • Targeted/untargeted attacks on object recognition and image segmentation models Cybersecurity: • Evade spam filters, malware detectors, network intrusion detection etc. Security: • Disappearance attacks against CCTV surveillance Adversarial Threats to AI Scenarios Undermine trust in AI
- 8. 8 Reports of cybersecurity vulnerabilities due to evasion attacks against AI in anti-malware / -virus products. Such attacks are already happening...
- 9. Adversarial Robustness Toolbox (ART) Repo: https://github.com/Trusted-AI/adversarial-robustness-toolbox Docs: https://adversarial-robustness-toolbox.readthedocs.io/ Demo: https://art-demo.mybluemix.net 9 Open-source release @ RSA 2018: Current stats: • 1.6K GitHub stars • 450+ forks • 250+ clones/w • 1K+ downloads/w • Python library, 12K lines of code • State-of-the-art attacks, defences and robustness metrics Load classifier model (Keras, TF, PyTorch etc) Perform attack Load ART modules Evaluate robustness LightGBM
- 10. • GitHub • https://github.com/Trusted-AI/adversarial-robustness-toolbox • Documentation • https://adversarial-robustness-toolbox.readthedocs.io • Slack • https://ibm-art.slack.com • Demo • https://art-demo.mybluemix.net/ • Blog • https://www.ibm.com/blogs/research/2019/09/adversarial-robustness-360-toolbox- v1-0 • White paper • https://arxiv.org/abs/1807.01069 • Tutorial • http://www.research.ibm.com/labs/ireland/nemesis2018/pdf/tutorial.pdf Resources & Conclusions https://www.research.ibm.com/artificial-intelligence/trusted-ai/
- 11. • Check Contributions page: • https://github.com/Trusted-AI/adversarial-robustness- toolbox/blob/main/CONTRIBUTING.md • Create github issues for suspected bugs, missing features, ideas for improvements etc. • Contribute bug fixes, new features etc. via pull requests to dev branch • Follow PEP 8 coding style, provide unit tests • Sign DCO (via ‘-s’ flag) for every commit ART – How to contribute?