Research on the Concept of Liquid State Machine

TL;DR

This paper reviews the Liquid State Machine (LSM), a neural model for real-time computation, highlighting that online learning yields better performance and simpler computation compared to batch learning.

Contribution

It provides a comparative analysis of online and offline learning methods for LSM, emphasizing the advantages of online learning in performance and complexity reduction.

Findings

Online learning achieves optimal LSM performance.

Batch learning introduces additional computational complexities.

Online method simplifies the training process.

Abstract

Liquid State Machine (LSM) is a neural model with real time computations which transforms the time varying inputs stream to a higher dimensional space. The concept of LSM is a novel field of research in biological inspired computation with most research effort on training the model as well as finding the optimum learning method. In this review, the performance of LSM model was investigated using two learning method, online learning and offline (batch) learning methods. The review revealed that optimal performance of LSM was recorded through online method as computational space and other complexities associated with batch learning is eliminated.