Training Neural Networks for Sensor
January 1, 2020Syntiant Engineering, 2019-20
Liaison(s): Dave Garrett, Atul Gupta
Advisor(s): David Harris
Students(s): Henry Limm (TL-S), Will McDonald, Vicki Moran (TL-F), Taylor Sloop, Maxime Vienne (FE-F), Yaqub Mahsud (S)
Syntiant’s Neural Decision Processor, the NDP101, can run a small neural network at a low energy cost, running off a coin cell battery. Currently, the NDP101 is used in devices to listen for words that activate a voice assistant. The Harvey Mudd Syntiant Clinic team explores the use of the NDP101 in a new setting. Instead of using a microphone, the team uses a sensor that measures movements. This sensor is part of a prototype that uses the NDP101’s neural network to recognize distinct hand gestures that a smartwatch might experience in daily use.