AI and ML blog

Large Language Models (LLMs), a form of generative AI inference, can now run on the majority of mobile devices built on the Arm CPU. This blog explains how and why.

Calling all developers who want to maximize their neural network performance! We present the Arm MLIA, the work leading up to it and why it matters.

How developers can optimize their AI models for Arm Ethos-U NPUs using the NVIDIA TAO Toolkit.

Arm has worked with Meta to introduce support for Arm platforms in ExecuTorch.

Current state of quantization on mobile (Android) is presented. Post-Training Quantization and Quantization Aware Training (QAT) in TFLite are discussed.

During the Game Developer Conference (GDC) in March 2023, we showcased our multi-agent demo called Candy Clash, which is a mobile game containing 100 intelligent agents.

Using the Unity ML-Agents Toolkit, we developed Candy Clash demo, the multi-agent system, where dozens of rabbit characters work as a team, aiming to crack their opponent's egg.

How to design a neural network so that the compiler is able to efficiently compress the weights of your ML model and benefit fully from the capabilities of the Ethos-U hardware?

Using the Unity ML-Agents Toolkit, we developed Candy Clash demo, the multi-agent system, where dozens of rabbit characters work as a team, aiming to crack their opponent's egg.

Using the Unity ML-Agents Toolkit, we developed Candy Clash demo, the multi-agent system, where dozens of rabbit characters work as a team, aiming to crack their opponent's egg.

In this blog, we demonstrate how to analyze a Machine Learning model on a layer-by-layer basis.

Join DSP Concepts and Alif Semiconductor at Arm DevSummit 2022 to discuss ML techniques commonly used for audio. Discover the features and benefits of the Audio Weaver platform.

This blog introduces how to deploy a PP-OCRv3 English text recognition model on Arm Cortex-M55 processor with Arm Virtual Hardware.

In this blog post, read about advancements in ML with Arm NN 2021.

As first step to deploy your NN model on Ethos-U, Vela Compiler is open-source and easy-use. Try it out and embrace the improvement of ML ability brought by Ethos-U to embedded system.

This blog post explains how to optimize a trained deep neural network model to run on Ethos-U55 and Ethos-U65.

This year’s Arm DevSummit Developer Competition winner explains how his wildfire detection solution uses tech to tackle real-life sustainability issues.

This Blog mainly introduced how Paddle-Lite improves performance of mobile devices with Arm technology, especially for CPU and Mali GPU.

Learn more about how the future of smart camera technology will bring with it profound transformations in the way we interact with each other and the world around us.

Build and deploy embedded machine learning applications for Arm Cortex-M55 CPU and Arm Ethos-U55 NPU with Arm ML Embedded Evaluation Kit.

Learn more about how to use Arm Streamline to profile different machine learning workloads for your applications.