YoVDO

System Software for Machine Learning at the Edge - tinyML Asia 2020

Offered By: tinyML via YouTube

Tags

Edge Computing Courses Machine Learning Courses Embedded Systems Courses Hardware Acceleration Courses Low-Power Computing Courses

Course Description

Overview

Explore system software approaches for machine learning at the edge in this tinyML Asia 2020 conference talk. Delve into the challenges and opportunities of deploying ML on mobile and IoT devices, focusing on compiler and runtime software strategies to maximize hardware potential. Learn about deep neural network optimizations, workload partitioning, and voltage-frequency scaling techniques for orchestrating on-chip compute resources. Discover how these methods can achieve low-power, real-time edge ML performance across various applications, from gesture recognition to fitness tracking. Gain insights into the evolving landscape of heterogeneous system-on-chips, TensorFlow Lite architecture, and the role of compilers in addressing fundamental problems in edge computing.

Syllabus

Introduction
Presentation
Machine Learning at the Edge
Finger and Hand Gesture Recognition
TI Sensor Tag
Arm Cortex M3
Fitness Tracking
Wearable SOC Trends
heterogeneous SOCs
Tensorflow Lite
Architecture
Accelerators
Universal Accelerators
Software Defined Hardware
GovTech IoT Stack
Scalable Compilation
Application Scenario
Questions
Singapore Smart City Ranking
Smart Nation Initiative
Heterogeneity
Fundamental Problems
Compilers
Role of Compilers
Thank you
Sponsor
ARM
Cortex
Media Partners
Conclusion


Taught by

tinyML

Related Courses

State of the TinyAutoML Market - Keynote
tinyML via YouTube
Sensing Applications as a Driver for TinyML Solutions
tinyML via YouTube
Accelerate Edge Compute with Syntiant's TinyML Platform
tinyML via YouTube
hls4ml: An Open-Source Co-Design Workflow for Scientific Low-Power Machine Learning Devices
tinyML via YouTube
TinyML Journey: From Face Detection Demo to Real-Life Commercial Deployment
tinyML via YouTube