Research on the Concept of Liquid State Machine
This is an incremental review for researchers in biologically inspired computation, focusing on training methods for LSM models.
The paper reviewed the Liquid State Machine (LSM) neural model, comparing online and offline learning methods, and found that online learning achieved optimal performance by eliminating computational space and complexities associated with batch learning.
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.