Главная
Study mode:
on
1
Intro
2
Building products vs doing projects
3
Condition Monitoring for an Industrial Blower
4
Al ExploreTM results - Explainability
5
Phase 1: Prove feasibility
6
Best sensors? Best location?
7
BOM Optimization - Channel Selection
8
BOM Optimization - Sensitivity
9
Phase 2: Design the product
10
Build production ML model
11
Data Readiness - Consistency
12
Data Readiness - Quality
13
Data Readiness - Category Coverage
14
Data Readiness - Time Coverage
15
Product development lifecycle
Description:
Explore the intricacies of building products using Edge AI and TinyML on microcontrollers in this 33-minute tinyML Talks webcast featuring Stuart Feffer from Reality AI. Discover how to leverage AI for sensor selection, placement optimization, and component specification determination while minimizing data collection costs. Learn to generate sophisticated, explainable machine learning models based on sensor data automatically using Reality AI Tools 4.0. Gain insights into the differences between project execution and product development through real-world case studies, including condition monitoring for an industrial blower. Delve into topics such as AI Explore results, feasibility proof, BOM optimization, production ML model building, and data readiness considerations throughout the product development lifecycle.

Building Products Using Edge AI - TinyML on MCUs

tinyML
Add to list