Use of the separation property to derive Liquid State Machines with enhanced classification performance

详细信息    查看全文

• 作者：Emmanouil Hourdakis^a ; ^b ; ^{ehourdak@ics.forth.gr}Author Vitae ; Panos Trahanias^a ; ^bAuthor Vitae
• 关键词：Liquid State Machines ; Separation ; Fisher Discriminant Ratio
• 刊名：Neurocomputing
• 出版年：2013
• 出版时间：1 May, 2013
• 年：2013
• 卷：107
• 期：Complete
• 页码：40-48
• 全文大小：1311 K

文摘

Liquid State Machines constitute a powerful computational tool for carrying out complex real time computations on continuous input streams. Their performance is based on two properties, approximation and separation. While the former depends on the selection of class functions for the readout maps, the latter needs to be evaluated for a particular liquid architecture. In the current paper we show how the Fisher's Discriminant Ratio can be used to effectively measure the separation of a Liquid State Machine. This measure is then used as a fitness function in an evolutionary framework that searches for suitable liquid properties and architectures in order to optimize the performance of the trained readouts. Evaluation results demonstrate the effectiveness of the proposed approach.