Many Shades of Acceleration - An Open TinyML Platform Perspective
Offered By: tinyML via YouTube
Course Description
Overview
Explore the future of Extreme Edge AI in this 55-minute keynote address from the tinyML Summit 2021. Delve into the challenges and opportunities of pushing signal processing and machine learning towards sensors and actuators with sub-mW power budgets. Learn about the balance between general-purpose and highly specialized architectures, drawing from the extensive experience of the open PULP platform. Discover insights on instruction-level acceleration, parallelization, and domain-specific acceleration engines based on RISC-V processors. Examine various hardware acceleration techniques, including binary base quantization and in-memory accelerators. Gain a comprehensive understanding of the full system aspects, always-on intelligence, power consumption considerations, and the benefits of an open platform approach in the realm of TinyML.
Syllabus
Intro
The big opportunity in business
Challenges
Energy Efficiency
Instruction Level Acceleration
Parallelization
Other components
Parallelisation
Continuous Platform
Hardware Acceleration Engine
Hardware Concrete Engine
Hardware Processing Engine
Compute Engine
Binary Base Quantization
Binary Engine
Conclusion
Full system aspect
Alwayson intelligence
Power consumption
Inmemory accelerator
Low power IOs
Open platform
Sponsors
Taught by
tinyML
Related Courses
Deploying TinyMLHarvard University via edX Learning TinyML
LinkedIn Learning Create and Connect Secure and Trustworthy IoT Devices
Microsoft via YouTube Speech-to-Intent on MCU: TinyML for Efficient Device Control - Lecture 6
Hardware.ai via YouTube Wio Terminal TinyML Course - People Counting and Azure IoT Central Integration - Part 3
Hardware.ai via YouTube