Learning for VMM + WTA Embedded Classifiers

Abstract : The authors present training and feedforwardcomputation for a single layer of a VMM WTA classifier.The experimental demonstration of the one-layer universalapproximator encourages the use of one-layer networks forembedded low-power classification. The results enablingcorrect classification of each novel acoustic signal(generator, idle car, and idle truck). The classificationstructure requires, after training, less than 30W ofoperational power and lower with additional fabrication.

[1]  Sihwan Kim,et al.  Integrated Floating-Gate Programming Environment for System-Level ICs , 2016, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[2]  Arindam Basu,et al.  A Learning-Enabled Neuron Array IC Based Upon Transistor Channel Models of Biological Phenomena , 2013, IEEE Transactions on Biomedical Circuits and Systems.

[3]  Paul E. Hasler,et al.  A Low-Power Programmable Bandpass Filter Section for Higher Order Filter Applications , 2007, IEEE Transactions on Circuits and Systems I: Regular Papers.

[4]  Jennifer Hasler,et al.  Vector-Matrix Multiply and Winner-Take-All as an Analog Classifier , 2014, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[5]  Sihwan Kim,et al.  A Programmable and Configurable Mixed-Mode FPAA SoC , 2016, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[6]  P. Hasler,et al.  A bio-physically inspired silicon neuron , 2004 .