Explore the latest advancements in Machine Learning solutions for embedded devices in this tinyML Asia 2020 conference talk. Delve into the world of micro-network processor units (micro-NPUs) and their impact on edge AI processing. Learn how Arm's Ethos-U micro-NPUs are revolutionizing low-cost, efficient AI solutions for endpoint and IoT devices. Discover the capabilities of Ethos-U55 and Ethos-U65, their performance comparisons, supported networks, and software flow. Gain insights into hardware repurposing, free simulators, and the potential applications unlocked by these innovative technologies.
Powering Innovation in AI Devices on the Edge with Micro-NPUs - tinyML Asia 2020
Overview
Syllabus
Intro
Welcome
AI is transforming everything
Endpoint AI solution
Ethos U55
Ethos U65
Applications
U55 vs U65
Supported networks
Software flow
EthosU
CortexM Performance
U65 Performance
Cortex A53 Performance
Simulation Models
Summary
Questions
Hardware repurposing
Free simulators
Sponsors
Taught by
tinyML
Related Courses
-
Creating End-to-End TinyML Applications for Ethos-U NPU in the Cloud
-
Endpoint AI Revolution Driven by Standardized Computing Platform
-
Energy-efficient On-device Processing for Next-generation Endpoint ML - tinyML Summit 2020
-
Tiny but Powerful: Hardware for High Performance, Low Power Machine Learning
-
Software-Driven TinyML Hardware Co-Design for AI Power Smart Devices
