Improved spikeprop for using particle swarm optimization

DOI10.1155/2013/257085MaRDI QIDQ460356zbMATH OpenOpenAlexWikidataFDO

Authors Falah Y. H. Ahmed, Siti Zaiton Mohd Hashim, Siti Mariyam Shamsuddin

Publication date 13 October 2014

Published in Mathematical Problems in Engineering (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1155/2013/257085

Mathematics Subject Classification ID

Approximation methods and heuristics in mathematical programming (90C59)

Review text

Summary: A spiking neurons network encodes information in the timing of individual spike times. A novel supervised learning rule for SpikeProp is derived to overcome the discontinuities introduced by the spiking thresholding. This algorithm is based on an error-backpropagation learning rule suited for supervised learning of spiking neurons that use exact spike time coding. The SpikeProp is able to demonstrate the spiking neurons that can perform complex nonlinear classification in fast temporal coding. This study proposes enhancements of SpikeProp learning algorithm for supervised training of spiking networks which can deal with complex patterns. The proposed methods include the SpikeProp particle swarm optimization (PSO) and angle driven dependency learning rate. These methods are presented to SpikeProp network for multilayer learning enhancement and weights optimization. Input and output patterns are encoded as spike trains of precisely timed spikes, and the network learns to transform the input trains into target output trains. With these enhancements, our proposed methods outperformed other conventional neural network architectures.

Recommendations

• A new supervised learning algorithm for spiking neurons
• Error-backpropagation in temporally encoded networks of spiking neurons
• Learning spatiotemporally encoded pattern transformations in structured spiking neural networks
• A supervised multi-spike learning algorithm based on gradient descent for spiking neural networks
• EVOLUTIONARY DESIGN OF SPIKING NEURAL NETWORKS

Cites work

• Error-backpropagation in temporally encoded networks of spiking neurons
• scientific article; zbMATH DE number 51537 (Why is no real title available?)
• scientific article; zbMATH DE number 928746 (Why is no real title available?)
• Integrative connectionist learning systems inspired by nature: Current models, future trends and challenges
• Learning Beyond Finite Memory in Recurrent Networks of Spiking Neurons
• Learning representations by back-propagating errors
• Spiking Neuron Models

Cited in

(4)

• The convergence analysis of spikeprop algorithm with smoothing \(L_{1/2}\) regularization
• Robust learning in SpikeProp
• EVOLUTIONARY DESIGN OF SPIKING NEURAL NETWORKS
• Adaptive learning rate of SpikeProp based on weight convergence analysis

This page was built for publication: Improved spikeprop for using particle swarm optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q460356)