A Digital Liquid State Machine With Biologically Inspired Learning and Its Application to Speech Recognition

Abstract

This paper presents a bioinspired digital liquid-state machine (LSM) for low-power very-large-scale-integration (VLSI)-based machine learning applications. To the best of the authors' knowledge, this is the first work that employs a bioinspired spike-based learning algorithm for the LSM. With the proposed online learning, the LSM extracts information from input patterns on the fly without needing intermediate data storage as required in offline learning methods such as ridge regression. The proposed learning rule is local such that each synaptic weight update is based only upon the firing activities of the corresponding presynaptic and postsynaptic neurons without incurring global communications across the neural network. Compared with the backpropagation-based learning, the locality of computation in the proposed approach lends itself to efficient parallel VLSI implementation. We use subsets of the TI46 speech corpus to benchmark the bioinspired digital LSM. To reduce the complexity of the spiking neural network model without performance degradation for speech recognition, we study the impacts of synaptic models on the fading memory of the reservoir and hence the network performance. Moreover, we examine the tradeoffs between synaptic weight resolution, reservoir size, and recognition performance and present techniques to further reduce the overhead of hardware implementation. Our simulation results show that in terms of isolated word recognition evaluated using the TI46 speech corpus, the proposed digital LSM rivals the state-of-the-art hidden Markov-model-based recognizer Sphinx-4 and outperforms all other reported recognizers including the ones that are based upon the LSM or neural networks.

Recent advances in physical reservoir computing: A review

“…The efficiency of the proposed architecture was demonstrated in a spike train classification task and an approximation task of retrieving the sum of firing rates of input spike trains. In another study, a biologically inspired local learning rule was presented for lowpower VLSI implementation of LSMs to reduce hardware implementation costs (Zhang et al, 2015). It was numerically shown that the overhead of hardware implementation can be reduced by the new learning rule in a speech recognition task.…”

Predicting Performance using Approximate State Space Model for Liquid State Machines

“…System is trained and for 200 epochs on 500 TI-46 spoken digit samples. Performance is evaluated using 5 fold testing where accuracy is averaged over the last 20 epochs [15]. Samples used in training and testing consisted of a uniform distribution of 50 samples for each digit '0-9' and 100 samples for each speaker, among 5 female speakers.…”

A novel digital neuromorphic architecture efficiently facilitating complex synaptic response functions applied to liquid state machines

“…LSMs have been successfully applied to several applications including speech recognition [10], vision [23], and cognitive neuroscience [11], [24]. Practical applications suffer from the fact that traditional LSMs take input in the form of spike trains.…”

“…We build upon these efforts leveraging the benefits of low energy consumption, scalability, and run time speed ups and include an efficient implementation of arbitrarily complex synaptic response functions in a digital architecture. This is important as the synaptic response function has strong implications in spiking recurrent neural networks [10].…”