AWS CEO Andy Jassy announced the inference chip, called AWS Inferentia, during his keynote at the cloud giant’s big annual conference in Las Vegas. The cloud market leader unveiled a new custom machine-learning chip called AWS Inferentia, designed specifically for inference tasks, in which machine-learning systems actually start to put patterns together after having been trained on a data set.
- Amazon Elastic Inference: Deep learning inference accerlation
- AWS Inferentia: Machine learning inference chip
- Amazon SageMaker Ground Truth: Build accurate ML training datasets
- Amazon SageMaker RL: Reinforcement learning for developer and data scientist
- AWS DeepRacer: Autonomous 1/18th scale race car, driven by ML
- Amazon Textract: Extract text and data from documents
- Amazon Personalize: Build real-time recommendations into your applications
- Amazon Forecast: Increase forecast accuracy using machine learning
- Amazon Elastic Inference：Fast, low-cost machine learning inference
Add GPU accerleration to any Amazon EC2 instance for faster inference at much lower cost (up to 75% savings).
- AWS Inferentia：Machine learning inference chip-High throughput/ Low latency/ Hundreds of TOPS
AWS Inferentia support Mutiple data types like INT8, FP16 and mix precision, as well as mutiple ML frameworks includes TensorFlow, MXNet, Caffe2, ONNX and PyTorch.
- Amazon SageMaker Ground Truth
Amazon SageMaker Ground Truth helps you build highly accurate training datasets for machine learning quickly. It offers easy access to public and private human labelers and provides them with built-in workflows and interfaces for common labeling tasks. Additionally, SageMaker Ground Truth can lower your labeling costs by up to 70% using automatic labeling, which works by training Ground Truth from data labeled by humans so that the service learns to label data independently.
- Amazon SageMaker RL：Reinforcement learning for every developer and data scientist
New machine learning capabilities in Amazon SageMaker to build, train, and deploy with reinforcement.
- AWS DeepRacer：World’s first global autonomous racing league, open to anyone.
- Amazon Textract：No ML experience required
This Optical Character Recognition (OCR) service will help you to extract text and data from virtually any document. Powered by Machine Learning, it will identify bounding boxes, detect key-value pairs, and make sense of tables, while eliminating manual effort and lowering your document-processing costs.
- Amazon Personalize
ML personalization and recommendations, commonly used in E-Commerce.
- Amazon Forecast-Machine learning time-series forcasting
This service helps you accurate time-series forecasting service, based on the same technology used at Amazon.com. No ML experience required.