Increase in Complexity in Random Neural Networks

@inproceedings{Cessac2017IncreaseIC,
  title={Increase in Complexity in Random Neural Networks},
  author={Bruno Cessac},
  year={2017}
}
We study trie dynamics of a discrete time, continuous state neural network with random asymmetric couplings and random thresholds. Trie evolution of trie neurons is given m the thermodynamic limit by a set of dynamic mean-field equations obtained by using a local chaos hypothesis. We study the evolution of trie mean quadratic distance between two trajectories, and show there exist two dioEerent regimes according to the value of trie control parameters. In the first Que (static regime) two… CONTINUE READING

References

Publications referenced by this paper.

Dynamique de réseaux de neurones à temps discret, 7èmes journées Neurosciences et sciences de l'ingénieur

  • A E.Patrick, V A.Zagrebnov
  • J. Phys. A
  • 1991

Similar Papers

Loading similar papers…