%0 Journal Article
%T Low Power Dendritic Computation for Wordspotting
%A Suma George
%A Jennifer Hasler
%A Scott Koziol
%A Stephen Nease
%A Shubha Ramakrishnan
%J Journal of Low Power Electronics and Applications
%D 2013
%I MDPI AG
%R 10.3390/jlpea3020073
%X 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/¦ÌW as compared to Digital Systems which perform 10 MMACs/mW.
%K computational modeling
%K hidden markov models
%K neuromorphic
%K dendrites
%U http://www.mdpi.com/2079-9268/3/2/73