Dynamic stochastic synapses as computational units
Neural Computation
Spiking Neuron Models: An Introduction
Spiking Neuron Models: An Introduction
2007 Special Issue: The cerebellum as a liquid state machine
Neural Networks
Which model to use for the liquid state machine?
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Adaptive learning procedure for a network of spiking neurons and visual pattern recognition
ACIVS'06 Proceedings of the 8th international conference on Advanced Concepts For Intelligent Vision Systems
Reservoir-based evolving spiking neural network for spatio-temporal pattern recognition
ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part II
ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part I
WCCI'12 Proceedings of the 2012 World Congress conference on Advances in Computational Intelligence
NeuCube evospike architecture for spatio-temporal modelling and pattern recognition of brain signals
ANNPR'12 Proceedings of the 5th INNS IAPR TC 3 GIRPR conference on Artificial Neural Networks in Pattern Recognition
| Hi-index | 0.00 |
An extension of an evolving spiking neural network (eSNN) is proposed that enables the method to process spatio-temporal information. In this extension, an additional layer is added to the network architecture that transforms a spatio-temporal input pattern into a single intermediate high-dimensional network state which in turn is mapped into a desired class label using a fast one-pass learning algorithm. The intermediate state is represented by a novel probabilistic reservoir computing approach in which a stochastic neural model introduces a non-deterministic component into a liquid state machine. A proof of concept is presented demonstrating an improved separation capability of the reservoir and consequently its suitability for an eSNN extension.