Graphics and Gaming
High Performance Computing
Open Source Software and Platforms
TrustZone for Armv8-M
Internet of Things
All developer forums
IP Product forums
Tool & Software forums
Open a support case
Arm Approved program
Arm Design Reviews
Arm Research Events
Arm Research requires membership for participation - click to join
Arm ML Research Lab
Machine learning is finding increasing application across all compute tasks. Our research enables the ubiquitous application of energy-efficient machine learning by developing advanced hardware, software, and algorithms for this rapidly evolving area.
Accelerate Machine Learning
Our researchers are developing advanced, energy efficient hardware, software, and tools to support complex algorithms. Explore the Arm Research Impact Report 2021 to learn more.
Devices, Circuits & Materials
Software & Services
Ensuring your AI is sure: Any place, anywhere, anytime
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.
April 9, 2021
Using multiple labels improves neural network learning
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.
February 22, 2021
Research for a sustainable future
René de Jong
To help companies find the breakthrough innovations needed to support the Global Goals, the UNGC set up the Young SDG Innovator Program, which our colleagues in Arm joined.
October 19, 2020
Efficient Bug Discovery with Machine Learning for Hardware Verification
For present-day microprocessors, it is even more challenging to identify bugs. Using (ML) to efficiently identify bugs, we've seen a 25% increase in efficiency than the default verification workflow. …
September 22, 2020
Reducing the Cost of Neural Network Inference with Residue Number Systems
The size and computational complexity of neural network models continues to grow exponentially. However, the increase in computational requirements presents a major challenge to their adoption. Could Residue…
August 21, 2020
Adapting Models to the Real World: On-Device Training for Edge Model Adaptation
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.
July 15, 2020
It is time for natively flexible processors
The story behind our flexible processors paper started with how to make billions of everyday things smart.
July 13, 2020
Scalable Hyperparameter Tuning for AutoML
Mango is an open source Python library for hyperparameter optimization, built for AutoML systems. Developed by Arm Research, Mango presents many useful features.
July 7, 2020
Even Faster Convolutions: Winograd Convolutions meet Integer Quantization and Architecture Search
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…
April 29, 2020
SCALE-Sim: A cycle-accurate NPU simulator for your research experiments
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…
April 21, 2020
TinyML Applications Require New Network Architectures
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…
February 13, 2020
A Year of Discovery: Arm Research 2019
2019 was yet another year of incredible technology discovery for Arm Research. Inspiring advancements have been made across the research community, and Arm Research has contributed to this. Our teams have…
January 6, 2020
Sparse Architecture Search (SpArSe): Democratizing and Enabling TinyML on Arm M-class
Microcontrollers (MCUs) are the ubiquitous computer of our time, being tiny, cheap, and low power. Often powered by using solar cell, they are in your watch, fridge, and your car will contain about thirty…
December 2, 2019
Skipping RNN State-updates Without Retraining the Original Model
Recurrent Neural Networks (RNNs) are used in tasks where the strict order of the input conveys certain information, and so are classed as an important algorithm. These networks are being deployed on resource…
November 25, 2019
Collaboration Case Study: Machine Learning Hardware with Harvard University
University engagements play a significant role in our partnerships at Arm Research, helping us extend our reach and build understanding of technologies as they emerge. Harvard University is one of those…
November 18, 2019
Alpha-Blending: Quantizing networks without using the STE
Increasingly, intelligent applications are using neural networks at their core to deliver new functionality to users. These applications include language understanding and translation, image recognition…
August 16, 2019
Taking Constrained ML to the Next Level
One the primary research thrusts of our ML Research Lab is investigating ways to bring more machine learning applications to Arm's products, and to make existing applications more efficient.
August 6, 2019
Efficient Hardware for Mobile Computer Vision via Transfer Learning
Mobile computing is on the rise, and currently moving into some really exciting new applications and form factors – augmented reality (AR) glasses, unmanned aerial vehicles (UAVs), automated driver assistance…
April 1, 2019