Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

AI-ML Solutions for Low-Power Edge Platforms - Challenges and Opportunities

tinyML via YouTube

Overview

Explore the challenges and opportunities of AI/ML solutions for low-power Edge platforms in this 55-minute tinyML Talks webcast. Dive into the complexities of implementing AI/ML applications on various Edge devices, from microcontroller-based systems to application processors and servers. Learn about the diverse compute types, operating systems, and acceleration libraries available for Edge computing. Discover how GMAC Intelligence is developing an on-device AI/ML library and API to simplify application development and enable on-device training. Gain insights into topics such as AlwaysOn AI, video attendance, face recognition, and leveraging tinyML. Explore hardware acceleration techniques, practical problems in low-power devices, and unique algorithms for Edge AI. Discuss the future of Edge AI and learn about emerging platforms like Deeplight, Edge Impulse, Kixo, and Reality AI.

Syllabus

Introduction
Reminder
tinyML India Chapter
Amit Mate Introduction
GMAC Introduction
Challenges
Workflow
Performance Comparison
Challenges in AlwaysOn AI
Example Use Case
Video Attendance
Face Recognition Attendance
How to leverage tinyML
Questions
Network acceleration
Multicore DSPs
Hardware accelerators
Cnn
Story time
Lowpower devices
Practical problems
Unique algorithms
Nested for loop
Edge AI trends
Is there a niche for tinyML
Future of Edge AI
Deeplight
Edge Impulse
Kixo
Reality AI
October 27th
Closing

Taught by

tinyML

Reviews

Start your review of AI-ML Solutions for Low-Power Edge Platforms - Challenges and Opportunities

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.