Low Power Dendritic Computation for Wordspotting

Journal of Low Power Electronics and Applications

Suma George¹  Jennifer Hasler²  Scott Koziol²  Stephen Nease² 

[1] Georgia Institute of Technology, Atlanta 30363, GA, USA;

关键词: computational modeling;    hidden markov models;    neuromorphic;    dendrites;   

DOI  :  10.3390/jlpea3020073

来源: mdpi

【 摘 要 】

In this paper, we demonstrate how a network of dendrites can be used to build the state decoding block of a wordspotter similar to a Hidden Markov Model (HMM) classifier structure. We present simulation and experimental data for a single line dendrite and also experimental results for a dendrite-based classifier structure. This work builds on previously demonstrated building blocks of a neural network: the channel, synapses and dendrites using CMOS circuits. These structures can be used for speech and pattern recognition. The computational efficiency of such a system is >10 MMACs/μW as compared to Digital Systems which perform 10 MMACs/mW.

【 授权许可】

CC BY   
© 2013 by the authors; licensee MDPI, Basel, Switzerland.