Главная
Study mode:
on
1
tiny ML. Talks
2
Harvey Mudd College Clinic Team
3
Harvey Mudd College Clinic Program
4
Problem Statement
5
More than Speech Recognition
6
Wrist-Based Gestures for Smartwatch Applications
7
Prototype Breakdown
8
Data Collection Hardware
9
Data Collection Involves Multiple Gestures
10
Typical Data Instances
11
Data Augmentation
12
Data Visualization
13
Network Architecture
14
Dataset Composition
15
Network Performance
16
Effect of Time Shifting
17
Framing for Input Window
18
Watch-Checking Demonstration
19
Benefits of a Custom Printed Circuit Board
20
Implementation of the Board
21
Components Consume Minimal Power
22
Other Components Enable Additional Features
Description:
Explore a tinyML Talks webcast featuring Vicki Moran and Will McDonald from Harvey Mudd College as they discuss training neural networks for sensors. Delve into the 2019-2020 Harvey Mudd College Clinic program, where a team of students collected data from a 6-axis accelerometer and trained neural networks to recognize gestures on a Syntiant NDP101 device. Learn about the project investigation, data collection process, and neural network performance achieved for three unique gestures. Discover insights on wrist-based gestures for smartwatch applications, data augmentation techniques, network architecture, and the effects of time shifting. Witness a watch-checking demonstration and understand the benefits of custom printed circuit boards in implementing low-power components for additional features.

Training Neural Networks for Sensors

tinyML
Add to list
0:00 / 0:00