Machine Learning Blog

The workshop held in conjunction with MLSys 2021 brought researchers and practitioners together to discuss key issues, share new research results and practical tutorial material.

This blog introduces the first Armv9 CPUs for a wide variety of consumer device segments.

This blog summarizes the new suite of Arm Mali GPUs that targets every single market segment for consumer compute.

This blog provides detailed information about Arm's new Total Compute solutions and the advance compute, security and developer experiences that they will empower.

Arm Research is excited to be part of the Cambridge ELLIS Unit, focusing on two key elements: Bayesian statistics and Probabilistic ML.

Arm is now releasing PyTorch and TensorFlow container images monthly. In this blog, let us look at what is available in our 21.04 release and what is coming in the future.

How do you enable your robot to navigate the complexities of world and be successful with the tasks & jobs you give them? Think about the elements that go into SLAM and learn about best practices for deployment…

This blog explores the key market and technology trends that will define the evolution of set-top box devices in the next three to five years.

It is important in industry to define what we see and how well we see it. This simple yet powerful idea has driven recent developments in the Arm Research ML Lab.

This blog post is about sharing our experience in running PyTorch Mobile with NNAPI on various mobile devices. I hope that this will provide developers with a sense of how these models are executed on…

This blog explains how developers can create fitness and exercise applications on Smart TVs for the end-user.

This blog explains how to get real time results with CNN inference for Augmented Reality (AR) on Mobile.

A single label is not enough. Label diversity can be introduced by creating several labels for each training example in a way that the ordinal structure allows.

This blog describes the process for building an augmented reality (AR) filter mobile app in Unity.

This blog demonstrates how to significantly reduce memory usage and achieve a substantial inference speed-up through enabling new Arm NN features.

This blog article introduces how to profile and optimize machine learning applications running with the Arm NN inference engine.

Arm and MLCommons, a global engineering consortium are working together to push industry benchmarks and best practices for AI.

What is TVM? A quick guide on why developers focused on ML Deployment should be aware.