Training a Hidden Markov Model with a Bayesian Spiking Neural Network

06/02/2016
by   Amirhossein Tavanaei, et al.
0

It is of some interest to understand how statistically based mechanisms for signal processing might be integrated with biologically motivated mechanisms such as neural networks. This paper explores a novel hybrid approach for classifying segments of sequential data, such as individual spoken works. The approach combines a hidden Markov model (HMM) with a spiking neural network (SNN). The HMM, consisting of states and transitions, forms a fixed backbone with nonadaptive transition probabilities. The SNN, however, implements a biologically based Bayesian computation that derives from the spike timing-dependent plasticity (STDP) learning rule. The emission (observation) probabilities of the HMM are represented in the SNN and trained with the STDP rule. A separate SNN, each with the same architecture, is associated with each of the states of the HMM. Because of the STDP training, each SNN implements an expectation maximization algorithm to learn the emission probabilities for one HMM state. The model was studied on synthesized spike-train data and also on spoken word data. Preliminary results suggest its performance compares favorably with other biologically motivated approaches. Because of the model's uniqueness and initial promise, it warrants further study. It provides some new ideas on how the brain might implement the equivalent of an HMM in a neural circuit.

READ FULL TEXT
research
11/25/2019

Biologically Plausible Sequence Learning with Spiking Neural Networks

Motivated by the celebrated discrete-time model of nervous activity outl...
research
06/26/2020

Biologically Plausible Learning of Text Representation with Spiking Neural Networks

This study proposes a novel biologically plausible mechanism for generat...
research
06/10/2017

Bio-Inspired Multi-Layer Spiking Neural Network Extracts Discriminative Features from Speech Signals

Spiking neural networks (SNNs) enable power-efficient implementations du...
research
06/02/2016

A Spiking Network that Learns to Extract Spike Signatures from Speech Signals

Spiking neural networks (SNNs) with adaptive synapses reflect core prope...
research
06/20/2017

Representation Learning using Event-based STDP

Although representation learning methods developed within the framework ...
research
06/04/2018

A Bayesian Penalized Hidden Markov Model for Ant Interactions

Interactions between social animals provide insights into the exchange a...
research
11/03/2022

To spike or not to spike: the whims of the Wonham filter in the strong noise regime

We study the celebrated Shiryaev-Wonham filter in its historical setup o...

Please sign up or login with your details

Forgot password? Click here to reset