AWS Machine Learning Blog

Deploying machine learning models as serverless APIs

Machine learning (ML) practitioners gather data, design algorithms, run experiments, and evaluate the results. After you create an ML model, you face another problem: serving predictions at scale cost-effectively. Serverless technology empowers you to serve your model predictions without worrying about how to manage the underlying infrastructure. Services like AWS Lambda only charge for the […]

Reducing player wait time and right sizing compute allocation using Amazon SageMaker RL and Amazon EKS

As a multiplayer game publisher, you may often need to either over-provision resources or manually manage compute allocation when launching or maintaining an online game to avoid long player wait times. You need to develop, configure, and deploy tools that help you monitor and control the compute allocation. This post demonstrates GameServer Autopilot, a new […]

Autodesk optimizes visual similarity search model in Fusion 360 with Amazon SageMaker Debugger

This post is co-written by Alexander Carlson, a machine learning engineer at Autodesk. Autodesk started its digital transformation journey years ago by moving workloads from private data centers to AWS services. The benefits of digital transformation are clear with generative design, which is a new technology that uses cloud computing to accelerate design exploration beyond […]

Pruning machine learning models with Amazon SageMaker Debugger and Amazon SageMaker Experiments

In the past decade, deep learning has advanced many different areas, such as computer vision and natural language processing. State-of-the-art models now achieve near-human performance in tasks such as image classification. Deep neural networks can achieve this because they consist of millions of parameters that you train on large training datasets. For instance, the BERT […]

Increasing performance and reducing the cost of MXNet inference using Amazon SageMaker Neo and Amazon Elastic Inference

When running deep learning models in production, balancing infrastructure cost versus model latency is always an important consideration. At re:Invent 2018, AWS introduced Amazon SageMaker Neo and Amazon Elastic Inference, two services that can make models more efficient for deep learning. In most deep learning applications, making predictions using a trained model—a process called inference—can […]

Analyzing and optimizing Amazon Lex conversations using Dashbot

This post is co-written by Arte Merritt, co-founder and CEO of Dashbot. In their own words, “Dashbot is an analytics platform for chatbots and voice skills that enables enterprises to increase engagement, satisfaction, and conversions through actionable insights and tools.” After you have deployed a bot, it is critical to analyze bot interactions, learn from […]

AWS delivers sessions online at NVIDIA GTC Digital

Starting Tuesday, March 24, 2020, NVIDIA GTC Digital is offering courses for you to learn AWS best practices to accomplish your ML goals faster and more easily. Registration is free, so register now. The following sessions are available from AWS: S22492: Train BERT in One Hour Using Massive Cloud Scale Distributed Deep Learning Learn how […]

Building a trash sorter with AWS DeepLens

April 2023 Update: Starting January 31, 2024, you will no longer be able to access AWS DeepLens through the AWS management console, manage DeepLens devices, or access any projects you have created. To learn more, refer to these frequently asked questions about AWS DeepLens end of life. In this blog post, we show you how to […]

Making accurate energy consumption predictions with Amazon Forecast

Amazon Forecast is a fully managed service that uses machine learning (ML) to generate highly accurate forecasts, without requiring any prior ML experience. Forecast is applicable in a wide variety of use cases, including energy demand forecasting, estimating product demand, workforce planning, and computing cloud infrastructure usage. With Forecast, there are no servers to provision […]

Investigating performance issues with Amazon CodeGuru Profiler

Amazon CodeGuru (Preview) analyzes your application’s performance characteristics and provides automatic recommendations on how to improve it. Amazon CodeGuru Profiler provides interactive visualizations to show you where your application spends its time. These flame graphs are a powerful tool to help you troubleshoot which code methods are causing delays or using too much CPU. This […]