Temporal pattern recognition via temporal networks of temporal neurons

Alex Frid, Hananel Hazan, Larry Manevitz

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We show that real valued continuous functions can be recognized in a reliable way, with good generalization ability using an adapted version of the Liquid State Machine (LSM) that receives direct real valued input. Furthermore this system works without the necessity of preliminary extraction of signal processing features. This avoids the necessity of discretization and encoding that has plagued earlier attempts on this process. We show this is effective on a simulated signal designed to have the properties of a physical trace of human speech. The main changes to the basic liquid state machine paradigm are (i) external stimulation to neurons by normalized real values and (ii) adaptation of the integrate and fire neurons in the liquid to have a history dependent sliding threshold (iii) topological constraints on the network connectivity.

Original languageAmerican English
Title of host publication2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2012
DOIs
StatePublished - 2012
Event2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2012 - Eilat, Israel
Duration: 14 Nov 201217 Nov 2012

Publication series

Name2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2012

Conference

Conference2012 IEEE 27th Convention of Electrical and Electronics Engineers in Israel, IEEEI 2012
Country/TerritoryIsrael
CityEilat
Period14/11/1217/11/12

Keywords

  • Classification
  • Liquid State Machine (LSM)
  • Signal Processing
  • Temporal Networks

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Temporal pattern recognition via temporal networks of temporal neurons'. Together they form a unique fingerprint.

Cite this