AWS re:invent 2019 | ML&AI Recap
Thanks to Accenture The Dock, I had the opportunity to attend the biggest tech event in the world alongside more than 60,000 AWS enthusiasts in Las Vegas from 2nd to 6th December. For someone attending the event for the first time, it was very overwhelming to see the scale of the event and amount of sessions running each day. It’s also hard to keep up with new features and services being launched at the event. I have tried to summarise major ML& AI announcements.
Amazon CodeGuru
One of the most cheered services, launched this year, CodeGuru provides code reviews and application performance recommendations. It helps to find the computationally expensive lines of code and gives you specific recommendations on how to fix or improve them. By simply adding Amazon CodeGuru as a reviewer, it can leave comments based on a model training against AWS internal code reviews, and code reviews from over 10,000 open source services. It can identify resource leaks, data race conditions between concurrent threads, and wasted CPU cycles. (more: Amazon CodeGuru)
Amazon Fraud Detector
Fraud Detector uses machine learning (ML) and 20 years of fraud detection expertise from AWS and Amazon.com to automatically identify potentially fraudulent activity so you can catch more fraud faster. With Fraud Detector, you can create a fraud detection model with just a few clicks and no prior ML experience because Fraud Detector handles all of the ML heavy liftings for you. (more: Fraud Detector)
Amazon Transcribe Medical — Speech Recognition
Amazon Transcribe Medical works as a speech to text streaming service to enable real-time transcription of patient visits. It can automatically and accurately transcribe physicians’ dictations, as well as their conversations with patients, into text. (more: Amazon Transcribe Medical)
Amazon Detective
Amazon Detective automatically collects log data from your AWS resources such as Virtual Private Cloud (VPC) Flow Logs, AWS CloudTrail, & Amazon GuardDuty and uses machine learning, statistical analysis, and graph theory to build a linked set of data that enables you to easily conduct faster and more efficient security investigations. Amazon Detective creates a unified, interactive view of your resources, users, and the interactions between them overtime with the ability to drill down into relevant historical activities, and quickly determine the root cause. (more: Amazon Detective)
Amazon Augmented AI
Amazon Augmented AI (Amazon A2I) makes it easy to build the workflows required for human review of ML predictions. A2I brings the human review to all developers, removing the undifferentiated heavy lifting associated with building human review systems or managing large numbers of human reviewers. (more: A2I guide)
SageMaker EcoSystem
SageMaker Autopilot
Just provide a tabular dataset and select the target column to predict, and SageMaker Autopilot automatically explores machine learning solutions with different combinations of data preprocessors, algorithms, and algorithm parameter settings, to find the most accurate model. SageMaker Autopilot also automatically tries different parameter settings on those algorithms to get the best model quality. You can now directly deploy the best model to production with just one click, or evaluate multiple candidates to trade-off metrics like accuracy, latency, and model size. (more: AWS Blog)
SageMaker Experiments
Machine learning is an iterative process. This iterative experimentation can result in hundreds and thousands of model training runs and model versions. Amazon SageMaker Experiments makes it easy to manage your machine learning experiments. It automatically tracks the inputs, parameters, configurations, and results of all your iterations as trials. (more: AWS blog)
SageMaker Debugger
Amazon SageMaker provides complete insights into the training process of machine learning (ML) models by automating the capture and analysis of data from training runs in real-time, with no code changes. When anomalies are detected, SageMaker Debugger sends alerts for developers’ to take remedial actions, reducing the time it takes to debug models from days to minutes. (more: AWS Blog)
SageMaker Model Monitor
Amazon SageMaker Model Monitor is a new capability of Amazon SageMaker that continuously monitors machine learning (ML) models in production, detects deviations such as data drift that can degrade model performance over time, and alerts you to take remedial actions. (more: AWS Blog)
SageMaker Studio
Amazon SageMaker Studio is a rich web-based IDE that unifies, at last, all the tools needed for ML development. Developers can write code, track experiments, visualize data, and perform debugging and monitoring all within a single, integrated visual interface, which significantly boosts developer productivity. (more: AWS Blog)
SageMaker addons:
SageMaker launched Operators for Kubernetes
SageMaker supports Deep Graph Library
Machine Learning Embark program
AWS Machine Learning Embark program is designed to help other organizations to train their workforce in Machine Learning and embark on ML journey. The program kicks off with a discovery day workshop to identify a business problem well suited for machine learning within the organization and continues as AWS provides training, coaching, and implementation support needed to solve the business problem. (more: ML Embark)
Thanks for reading.
source:
