CNS '97 Proceedings of the sixth annual conference on Computational neuroscience : trends in research, 1998: trends in research, 1998
Face recognition by elastic bunch graph matching
Intelligent biometric techniques in fingerprint and face recognition
Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Spiking Neuron Models: An Introduction
Spiking Neuron Models: An Introduction
Evolving Connectionist Systems: Methods and Applications in Bioinformatics, Brain Study and Intelligent Machines
Adaptive Spiking Neural Networks for Audiovisual Pattern Recognition
Neural Information Processing
Natural Computing: an international journal
ICONIP '09 Proceedings of the 16th International Conference on Neural Information Processing: Part II
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Text-independent speaker authentication with spiking neural networks
ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I
FPGA implementation of an evolving spiking neural network
ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I
Integrated feature and parameter optimization for an evolving spiking neural network
ICONIP'08 Proceedings of the 15th international conference on Advances in neuro-information processing - Volume Part I
Optimization methods for spiking neurons and networks
IEEE Transactions on Neural Networks
Spike-timing-dependent construction
Neural Computation
Hi-index | 0.00 |
This paper presents an on-line training procedure for a hierarchical neural network of integrate-and-fire neurons. The training is done through synaptic plasticity and changes in the network structure. Event driven computation optimizes processing speed in order to simulate networks with large number of neurons. The training procedure is applied to the face recognition task. Preliminary experiments on a public available face image dataset show the same performance as the optimized off-line method. A comparison with other classical methods of face recognition demonstrates the properties of the system.