SSNNS -: a suite of tools to explore spiking neural networks

We are interested in engineering smart machines that enable backtracking of emergent behaviors. Our SSNNS simulator consists of hand-picked tools to explore spiking neural networks in more depth with flexibility. SSNNS is based on the Spike Response Model (SRM) with capabilities for short and long term memory. A genetic algorithm, namely CHC, is used independently to generate such example systems that produce patterns of interest. Foundational work in the growing field of spiking neural networks has shown that precise spike timing may be biologically more plausible and computationally powerful than traditional rate-based models[4][7]. We have been using evolution to discover neural configurations that produce patterns of interest. Categories and Subject Descriptors G.3 [Mathematics of Computing]: Probability and Statistics—Experimental Design, Time Series Analysis ; I.6.4 [Computing Methodologies]: Simulation and Modeling—Model Validation and Analysis General Terms Algorithms, ...

• Type: Conference
• Year: 2008
• Where: GECCO
• Authors: Heike Sichtig, J. David Schaffer, Craig B. Laramee
• Keywords: GECCO 2008, Genetic Algorithms, Neural Networks, Optimization, Spike Response Model