Machine Learning on Arm

Artificial Intelligence (AI) unleashes a new wave of innovation, powering new applications and business models in multiple markets. The Arm hardware and software technologies ecosystem enables the development of intelligent, distributed, heterogeneous, and secure solutions.

Project Trillium

Project Trillium, Arm’s Machine Learning (ML) platform, enables a new era of advanced, ultra-efficient inference at the edge. Specifically designed for ML and neural network (NN) capabilities, the architecture is versatile enough to scale to any device, from IoT to connected cars and servers.

Dev Day 

Learn about some of the key building blocks needed to develop intelligent machines.

Dev Day on demand

Arm ML processor

Based on a new, class-leading architecture, the Arm Machine Learning processor provides a huge uplift in efficiency compared to CPUs, GPUs and DSPs.
Read more

Arm Cortex-A Series

The Arm Cortex-A series of applications processors provide a range of solutions for devices undertaking complex compute tasks.
Read more

Arm Cortex-R Series

The Arm Cortex-R series provides a range of processors optimized for high performance, hard real-time applications.
Read more

Arm Cortex-M Series

The Arm Cortex-M series contains the smallest/lowest power processors build by Arm, optimized for discrete processing and microcontrollers.
Read more

Arm NN

Arm NN translates existing neural network frameworks, allowing them to run efficiently across Arm Cortex-A CPUs and Arm Mali GPUs.
Read more

Arm Compute Library

The Arm Compute Library is a collection of low-level functions optimized for Arm Cortex-A CPUs and Arm Mali GPUs, targeting computer vision and ML.
Read more

Be part of our ecosystem

We are growing our partnerships for machine learning solutions and would love for you to be a part of it. Get in touch with us to learn more and start promoting your solutions here.

Apply now

Life-changing asthma care

One in 12 people suffer from asthma. The Arm-powered Amiko Respiro uses machine learning to make treating and living with the condition easier.

View

A cure for loneliness

Half of all elderly adults living alone report suffering from loneliness. Intuition Robotics’ social robot, ElliQ, uses machine learning and cloud robotics to encourage an active and engaged lifestyle.

View

Cough monitor

Hundreds of millions of people worldwide live with chronic respiratory disorders. The Quvium Sonasure cough monitor uses machine learning to track early symptoms, inform treatment plans, and send alerts if emergency action is needed.

View

Get Support

Community Blogs

Blog post image
How to implement voice and audio processing on Arm with Alango Technologies

Picture your smart assistant at home: you say a command, and it recognizes your voice, processes what you’re saying and responds. This is an example of a multi-sensor device that requires signal processing. Read this blog to learn how to implement…

yesterday by Chris Shore
Blog post image
Arm School Program – The Royal Society and the future of mathematics

Arm has become a founding supporter of a research project by The Royal Society to investigate the future of the schools mathematics curriculum. Arm’s involvement has been driven by the Arm School Program.

2 days ago by Nicholas Sample
Blog post image
Logic-compatible Gain Cell eDRAM: A Real Alternative to SRAM

Andreas Burg, Associate Professor at EPFL, joined us at last year's Research Summit to discuss Gain Cell eDRAM as an alternative to conventional SRAM memories.

4 days ago by Charlotte Christopherson
Blog post image
Getting started with Docker for Arm using buildx on Linux

The multi-architecture support in Docker simplifies embedded Linux application development and deployment when targeting Arm embedded systems.

6 days ago by Jason Andrews
Blog post image
How GuardKnox is innovating automotive cybersecurity

GuardKnox is at the forefront of the automotive shift to generate in-vehicle high-performance computing platforms for security. Find out how they are innovating with a flexible and scalable electronic architecture.

7 days ago by Louise Paul
Blog post image
IWOCL - Enhanced Support for OpenCL Open Source Tools and Resources

Arm and The Khronos Group help refine and define open standards for OpenCL including the Clang project.

8 days ago by Anastasia Stulova

Community Forums

Answered Save tensorflow model for ArmNN
  • Machine Learning (ML)
  • TensorFlow
  • Arm NN
 0 votes 241 views 3 replies Latest 7 days ago by GeraldK Answer this
Answered how to add api to arm
  • api
 0 votes 512 views 2 replies Latest 1 months ago by Zhifei Yang Answer this
Answered ARM NN with ONNX Parser
  • Neural Network
  • Compilers
 0 votes 487 views 2 replies Latest 2 months ago by Anto85 Answer this
Answered [ARM NN on Raspberry PI] libarmnn.so: undefined reference to `powf@GLIBC_2.27'
  • Raspberry Pi
  • Neural Network
  • TensorFlow
 0 votes 1125 views 6 replies Latest 3 months ago by uccoder hk Answer this
Answered ARM NN build failed when linking libarm_compute_core-static.a
  • Cortex-A53
  • Arm NN
  • Arm Compute Library (ACL)
  • SIMD and Vector Execution
 0 votes 1392 views 3 replies Latest 9 months ago by Jason Andrews Answer this
Answered Matrix Multiplication Example in Arm Compute Library
  • Arm Compute Library (ACL)
 0 votes 3614 views 3 replies Latest 1 years ago by cdicker Answer this
Answered Save tensorflow model for ArmNN Latest 7 days ago by GeraldK 3 replies 241 views
Answered how to add api to arm Latest 1 months ago by Zhifei Yang 2 replies 512 views
Answered ARM NN with ONNX Parser Latest 2 months ago by Anto85 2 replies 487 views
Answered [ARM NN on Raspberry PI] libarmnn.so: undefined reference to `powf@GLIBC_2.27' Latest 3 months ago by uccoder hk 6 replies 1125 views
Answered ARM NN build failed when linking libarm_compute_core-static.a Latest 9 months ago by Jason Andrews 3 replies 1392 views
Answered Matrix Multiplication Example in Arm Compute Library Latest 1 years ago by cdicker 3 replies 3614 views