Machine Learning Blog

In this blog, written by Vikrant Tomar, Sam Myer and Kirsten Joe of Fluent.ai, read about multilingual speech recognition for Arm Cortex MCUs.

In this blog, read about Platform Security Architecture (PSA) and the Security Architecture Toolbox used to protect Machine Learning (ML) models on the edge.

In this blog, read about what COVID-Net is doing in embedded healthcare.

Neural networks are becoming widely used in computer interaction, but in real-world scenarios we see errors. We’ve recently completed research into edge distillation to solve this problem.

The story behind our flexible processors paper started with how to make billions of everyday things smart.

Mango is an open source Python library for hyperparameter optimization, built for AutoML systems. Developed by Arm Research, Mango presents many useful features.

Read this blog from Alexander Eroma, head of Intelligence at Octonion about collaborative learning with Arm MCUs.

In this blog, read about TinyML and the optimization of TVM.

Join Arm's AI virtual tech talk series covering the latest trends in machine learning development, including deployment, optimization, best practices, as well as new ML technologies shaping the industry…

Read this introduction to the Arm Cortex-X Custom Program, outlining what the new program entails and providing details about the new Arm Cortex-X1 CPU which is part of the program.

This blog explores the key features and benefits of the Arm Ethos-N78 NPU.

This blog explores the key features and benefits of the Arm Cortex-A78 CPU.

This blog goes through the key features and benefits of the Arm Mali-G78 GPU.

The design of deep learning (DL) neural network (NN) models targeting mobile devices has advanced rapidly over the last couple of years. Important computer vision tasks have led a community-wide transition…

Architecture simulators are a key tool in the computer architecture toolbox. They provide a convenient model of real hardware at a level of abstraction that makes them faster and more flexible than low…

Read about how to train a TinyML model to recognize sounds.

Introducing Total Compute and how it will provide the necessary performance for full digital immersion on next-generation devices.

Researchers have studied neural network compression for quite some time. However, the need for always on compute has led to a recent trend towards executing these applications on even smaller IoT devices…