Indirect differentiation of function for a network of biologically plausible neurons

Authors:
Amber D. Fischer;Cihan H. Dagli
Affiliations:
Smart Engineering Systems Laboratory, Department of Engineering Management, University of Missouri-Rolla, Rolla, MO;Smart Engineering Systems Laboratory, Department of Engineering Management, University of Missouri-Rolla, Rolla, MO
Venue:
ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
Year:
2003

Citing 7
Cited 0

A neural cocktail-party processor

Biological Cybernetics
Networks of spiking neurons: the third generation of neural network models

Transactions of the Society for Computer Simulation International - Special issue: simulation methodology in transportation systems
Collective excitation phenomena and their applications

Pulsed neural networks
Solving Nonlinear Optimization Problems Using Networks Of Spiking Neurons

IJCNN '00 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 6 - Volume 6
Perceptual groupings in a self-organizing map of spiking neurons

Perceptual groupings in a self-organizing map of spiking neurons
Synchronization and desynchronization in a network of locally coupled Wilson-Cowan oscillators

IEEE Transactions on Neural Networks
Self-organization of spiking neurons using action potential timing

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper introduces a new method to model differentiation of biologically plausible neurons, introducing the capability for indirectly defining the characteristics for a network of spiking neurons. Due to its biological plausibility and greater potential for computational power, a spiking neuron model is employed as the basic functional unit in our system. The method for designing the architecture (network design, communication structure, and neuron functionality) for networks of spiking neurons has been purely a manual process. In this paper, we propose a new design for the differentiation of a network of spiking neurons, such that these networks can be indirectly specified, thus enabling a method for the automatic creation of a network for a predetermined function. In this manner, the difficulties associated with the manual creation of these networks are overcome, and opportunity is provided for the utilization of these networks more readily for applications. Thus, this paper provides a new method for indirectly constructing these powerful networks, such as could be easily linked to an evolutionary system or other optimization algorithm.