Learning for VMM + WTA Embedded Classifiers

Abstract

The authors present training and feed forward computation for a single layer of a VMM WTA classifier. The experimental demonstration of the one-layer universal approximator encourages the use of one-layer networks for embedded low-power classification. The results enabling correct classification of each novel acoustic signal(generator, idle car, and idle truck). The classification structure requires, after training, less than 30microW of operational power and lower with additional fabrication.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 31, 2016
Accession Number
AD1025388

Entities

People

  • Jennifer Hasler
  • Sahil Shah

Organizations

  • Georgia Tech

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Acoustic Signals
  • Algorithms
  • Bandpass Filters
  • Computations
  • Data Sets
  • Deep Learning
  • Detection
  • Detectors
  • Energy Consumption
  • Engineering
  • Fabrication
  • Filters
  • Frequency
  • Machine Learning
  • Measurement
  • Neural Networks
  • Power Supplies

Readers

  • Integrated Circuit Design and Technology.
  • Neural Network Machine Learning.