Journal of Low Power Electronics and Applications · 2013 · 36 citations · 18 references
ComputingComputer ScienceComputer SystemsArtificial IntelligenceMachine LearningNeural CircuitryDendritic ComputationDendritic StructureHidden Markov ModelsNeural CircuitsNeural NetworksSpeech RecognitionCmos Logic CircuitsComputational EfficiencyComputational Efficiency AnalysisDendritic ArchitectureDendritic SpinesDendritic Tree ArchitectureHidden Markov Model TrainingNeural Network Modeling
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.
18
Hidden Markov Models for Speech Recognition
B.-H. Juang, L. R. Rabiner · Technometrics · 1991 · 688 citations
Hidden Markov Models for Speech Recognition
B.-H. Juang, L. R. Rabiner · Technometrics · 1991 · 608 citations