Maximization of mutual information in a linear noisy network: a detailed study

@inproceedings{Campa1995MaximizationOM,
  title={Maximization of mutual information in a linear noisy network: a detailed study},
  author={A Jorge Luis Campa and Paolo Del Giudice and N{\'e}stor Parga and Jean-Pierre Nadal},
  year={1995}
}
We consider a linear. one-layer feedforward ne& nehvork performing a coding task. The goal of the network is to provide a statistical neural representation that. conveys as much information as possible on the input stimuli in noisy conditions. We determine the family of synaptic couplings that maximizes the mutual information between input and output distribution. Optimization is performed under different constraints on the synaptic efficacies. We analyse the dependence of the solutions on… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 11 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 18 REFERENCES

Desimine receutive fields for hiehest fidelitv Network

  • D LRuderman
  • 1994

Desimine receutive fields for hiehest fidelitv Network 5 14755 Inf . 1

  • L RudermanD
  • Mod Phys . C
  • 1994

N e d neiworks as optimal information processors

  • A Campa, J-P De Giudice P. Nadal, N Parga
  • 1994

Inlroduclion to the Theory of Neural Compufnlion

  • J AHem, A Kmgh, R GPalmer
  • 1991

Color coding and its interaction with spatlotemporat processing

  • J IAtick, Z Li, A NRedlich
  • 1990

Hebbian leaming of principal components Parallel Pmcessing inNeural System and Compufers ed R Eckmiller

  • A Krogh, Hem
  • G -ann and G Hanske (Amsterdam: Elsevier)
  • 1990

The coding of sensory messages Curre " ! Problem in Animal Behaviour

  • B BarlowH
  • 1990

Similar Papers

Loading similar papers…