UZH ETH UZH|ETH
  Zurich

Skip to content. | Skip to navigation

Sections
Personal tools
You are here: Home Projects EvoSpike

EvoSpike

by Nikola Kasabov last modified Jun 27, 2012 12:05 PM
Evolving Probabilistic Spiking Neural Networks for Spatio-Temporal Pattern Recognition - an EU FP7 Marie Curie Project PIIF-GA-2010-272006, 2011-2012
Marie Curie Actions logo FP7 logo UZH-ETH Zurich logo KEDRI logo AUT logo

Project PDF flyer.

Background

Spatio- and spectro-temporal data (SSTD) are the most common type of data collected in many domain areas, including engineering, bioinformatics, neuroinformatics, ecology, environment, medicine, economics, etc. However, there is lack of methods for the analysis of such data, for the discovery of complex spatio-temporal patterns in it and for spatio-temporal pattern recognition (STPR). The brain functions as a spatio-temporal information processing machine and deals extremely well with spatio-temporal data. Its organisation and functions have been the inspiration for the development of new methods for SSTD analysis and STPR. The brain-inspired spiking neural networks (SNN), considered the third generation of neural networks, are a promising paradigm for the creation of new intelligent ICT for SSTD. This new generation of computational models and systems are potentially capable of modelling complex information processes due to their ability to represent and integrate different information dimensions, such as time, space, frequency, phase, and to deal with large volumes of data in an adaptive and self-organising manner. Goals and objectives The project develops novel methods and systems of SNN for SSTD analysis and STPR, namely evolving probabilistic spiking neural networks (epSNN) and evolving probabilistic computational neuro-genetic models (epCNGM). Software and hardware implementations and some pilot applications for audio-visual pattern recognition, EEG data analysis, and neurogenetic cognitive systems are also being developed.

The epSNN are built on the principles of evolving connectionist systems, of eSNN and of probabilistic neuronal models, previously developed by prof. Kasabov’s group at KEDRI. The latter extend the widely used leaky integrate-and-fire spiking model by introducing some biologically plausible probabilistic parameters. The epSNN are evolving structures that learn from and adapt to new incoming data. The research explores a range of approaches to creating epSNN for STPR, from a single neuron to ‘reservoir’ computing and neuro-genetic systems.

Objectives

The EvoSpike project develops novel methods and systems of SNN for SSTD, namely evolving probabilistic spiking neural networks (epSNN) and evolving probabilistic computational neuro-genetic models (epCNGM). Software and hardware implementations and some pilot applications for audio-visual pattern recognition, EEG data analysis, and neurogenetic cognitive systems are also being developed.

Participants

From the incoming organization KEDRI:

  • Prof. Nikola Kasabov (nkasabov@aut.ac.nz)
  • Dr A.Mohhemed
  • Dr S.Schliebs
  • K.Dhoble
  • N.Nuntalid
  • J.Bopp - a visiting student to KEDRI from Univ.of Appl.Sciences, Mannheim
  • N.Scott
  • Dr Haza Nuzlu

From the host institution INI:

  • Prof. Giacomo Indiveri
  • Fabio Stefanini
  • Sadique Sheik

(Part of) the EvoSpike project participants

EvoSpike team members

From left to right: F. Stefanini, Dr. G. Indiveri, Prof. N. Kasabov and K. Dhoble