An Evolutionary Strategy for Supervised Training of Biologically Plausible Neural Networks

@inproceedings{Belatreche2003AnES,
  title={An Evolutionary Strategy for Supervised Training of Biologically Plausible Neural Networks},
  author={Ammar Belatreche and Liam P. Maguire and Martin McGinnity and Q. X. Wu},
  year={2003}
}
Spiking neural networks represent a more plausible model of real biological neurons. In contrast to the classical artificial neural networks, which adopt a high abstraction of real neurons, spiking neurons consider time as an important feature for information representation and processing. However, good training algorithms are needed for better exploitation of these realistic models. Most existing learning paradigms adjust the synaptic weights in an unsupervised way based on the adaptation of… CONTINUE READING

References

Publications referenced by this paper.
Showing 1-8 of 8 references

SpikeProp: Error-Backpropagation for Networks of Spiking Neurons

  • S. M. Bohte, H. La Poutré, J. N. Kok
  • ESANN '
  • 2000
Highly Influential
5 Excerpts

An Overview of Evolutionary Algorithms for Parameter Optimization

  • T. Bäck, Schwefel H.-P.
  • Evol. Comput., Vol. 1, No. 1, pp. 1– 23, 1993.
  • 1993
1 Excerpt

Similar Papers

Loading similar papers…