TY - GEN
T1 - The liquid state machine is not robust to problems in its components but topological constraints can restore robustness
AU - Hazan, Hananel
AU - Manevitz, Larry
PY - 2010
Y1 - 2010
N2 - The Liquid State Machine (LSM) is a method of computing with temporal neurons, which can be used amongst other things for classifying intrinsically temporal data directly unlike standard artificial neural networks. It has also been put forward as a natural model of certain kinds of brain functions. There are two results in this paper: (1) We show that the LSM as normally defined cannot serve as a natural model for brain function. This is because they are very vulnerable to failures in parts of the model. This result is in contrast to work by Maass et al which showed that these models are robust to noise in the input data. (2) We show that specifying certain kinds of topological constraints (such as "small world assumption"), which have been claimed are reasonably plausible biologically, can restore robustness in this sense to LSMs.
AB - The Liquid State Machine (LSM) is a method of computing with temporal neurons, which can be used amongst other things for classifying intrinsically temporal data directly unlike standard artificial neural networks. It has also been put forward as a natural model of certain kinds of brain functions. There are two results in this paper: (1) We show that the LSM as normally defined cannot serve as a natural model for brain function. This is because they are very vulnerable to failures in parts of the model. This result is in contrast to work by Maass et al which showed that these models are robust to noise in the input data. (2) We show that specifying certain kinds of topological constraints (such as "small world assumption"), which have been claimed are reasonably plausible biologically, can restore robustness in this sense to LSMs.
KW - Liquid state machine
KW - Machine learning
KW - Robustness
KW - Small world topology
UR - https://www.scopus.com/pages/publications/78651414590
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:78651414590
SN - 9789898425324
T3 - ICFC 2010 ICNC 2010 - Proceedings of the International Conference on Fuzzy Computation and International Conference on Neural Computation
SP - 258
EP - 264
BT - ICFC 2010 ICNC 2010 - Proceedings of the International Conference on Fuzzy Computation and International Conference on Neural Computation
T2 - International Conference on Neural Computation, ICNC 2010 and of the International Conference on Fuzzy Computation, ICFC 2010
Y2 - 24 October 2010 through 26 October 2010
ER -