Character Recognition using Spiking Neural Networks
- 1 August 2007
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2007 International Joint Conference on Neural Networks
- No. 21614393,p. 53-58
- https://doi.org/10.1109/ijcnn.2007.4370930
Abstract
A spiking neural network model is used to identify characters in a character set. The network is a two layered structure consisting of integrate-and-fire and active dendrite neurons. There are both excitatory and inhibitory connections in the network. Spike time dependent plasticity (STDP) is used for training. The winner take all mechanism is enforced by the lateral inhibitory connections. It is found that most of the characters are recognized in a character set consisting of 48 characters. The network is trained successfully with increased resolution of the characters. Also, addition of uniform random noise does not decrease its recognition capability.Keywords
This publication has 18 references indexed in Scilit:
- Temporal sequence detection with spiking neurons: towards recognizing robot language instructionsConnection Science, 2006
- Scalable Massively Parallel Artificial Neural NetworksPublished by American Institute of Aeronautics and Astronautics (AIAA) ,2005
- Spike Timing-Dependent Plasticity of Neural CircuitsNeuron, 2004
- Spike-timing-dependent synaptic plasticity: from single spikes to spike trainsNeurocomputing, 2004
- Spike-Timing Dependent Competitive Learning of Integrate-and-Fire Neurons with Active DendritesLecture Notes in Computer Science, 2002
- Synaptic modification in neural circuits: A timely actionBioEssays, 2002
- Spatial and temporal pattern analysis via spiking neuronsNetwork: Computation in Neural Systems, 1998
- Regulation of Synaptic Efficacy by Coincidence of Postsynaptic APs and EPSPsScience, 1997
- Evoked Potential Studies of Face and Object ProcessingVisual Cognition, 1996
- Visual neurones responsive to faces in the monkey temporal cortexExperimental Brain Research, 1982