Next Article in Journal
Low-Power and Optimized VLSI Implementation of Compact Recursive Discrete Fourier Transform (RDFT) Processor for the Computations of DFT and Inverse Modified Cosine Transform (IMDCT) in a Digital Radio Mondiale (DRM) and DRM+ Receiver
Next Article in Special Issue
A Digital Auto-Zeroing Circuit to Reduce Offset in Sub-Threshold Sense Amplifiers
Previous Article in Journal / Special Issue
Exploration of Sub-VT and Near-VT 2T Gain-Cell Memories for Ultra-Low Power Applications under Technology Scaling
J. Low Power Electron. Appl. 2013, 3(2), 73-98; doi:10.3390/jlpea3020073
Article

Low Power Dendritic Computation for Wordspotting

* ,
,
,
 and
Georgia Institute of Technology, Atlanta 30363, GA, USA
* Author to whom correspondence should be addressed.
Received: 6 February 2013 / Revised: 7 April 2013 / Accepted: 19 April 2013 / Published: 21 May 2013
(This article belongs to the Special Issue Selected Papers from SubVt 2012 Conference)
View Full-Text   |   Download PDF [1436 KB, uploaded 21 May 2013]   |  

Abstract

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.
Keywords: computational modeling; hidden markov models; neuromorphic; dendrites computational modeling; hidden markov models; neuromorphic; dendrites
This is an open access article distributed under the Creative Commons Attribution License (CC BY 3.0).
SciFeed

Share & Cite This Article

Further Mendeley | CiteULike
Export to BibTeX |
EndNote |
RIS
MDPI and ACS Style

George, S.; Hasler, J.; Koziol, S.; Nease, S.; Ramakrishnan, S. Low Power Dendritic Computation for Wordspotting. J. Low Power Electron. Appl. 2013, 3, 73-98.

View more citation formats

Article Metrics

For more information on the journal, click here

Comments

[Return to top]
J. Low Power Electron. Appl. EISSN 2079-9268 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert