November, 2023 - Vol. 1
Welcome to our first GGR ML newsletter!
We offer a review of the embedded AI + ML space, reporting on both semiconductor IP and software with a focus on deeply embedded low power edge based devices.
Our monthly newsletter will offer the following.
A review of one of our own low power ML projects
News in Brief
Getting started in Embedded AI and ML
In next month's newsletter we will take a look at the ARM U-55 uNPU (Micro Neural Processing Unit). It is gaining wide usage with ARM licensees in low power edge devices. We will highlight one implementation (Alif Semiconductor) and show how a Tensorflow Lite model is mapped onto the uNPU hardware to improve inference performance.
News in Brief
Semiconductor companies are beefing up their ML portfolios.
TinyML and computer vision.
TinyML computer vision is turning into reality with microNPUs (uNPUs) offers a good overview of the near term potential for edge vision processing. Note particularly the ARM A55 and Ethos uNPU speed comparison near the end of the article.
A selection of hardware and software products that have caught our attention in the last month.
L3F Touch sensor for Robotic Arms
Maccarone is an experimental interface between Python code and ChatGPT which allows ChatGPT to dynamically control maintenance of sections of code using simple markups. It requires a paid ChatGPT account and works best with Visual Studio. Check out the animation part way down the github page to see how it works.
Getting Started in Embedded AI / ML
Just getting started in the deeply embedded AI + ML world? We will regularly update our recommended short courses and reading material.
Andrew Ng’s Coursera course is a great entry point to a more formal understanding of ML models and minimization functions and ultimately understanding the architectures behind the plethora of silicon based hardware accelerators hitting the market.
AI + ML projects have unique workflows that include elements from traditional Software Development (eg. CI/CD – Continuous Integration/ Continuous Development) along with large data set management and run-to-run tracking of model accuracy.
Chip Huyen’s book “Designing Machine Learning Systems” is required reading for anyone setting up Machine Learning pipelines.