Nets with Unreliable Hidden Nodes Learn Error-Correcting Codes

@inproceedings{Judd1992NetsWU,
  title={Nets with Unreliable Hidden Nodes Learn Error-Correcting Codes},
  author={J. Stephen Judd and Paul W. Munro},
  booktitle={NIPS},
  year={1992}
}
In a multi-layered neural network, anyone of the hidden layers can be viewed as computing a distributed representation of the input. Several "encoder" experiments have shown that when the representation space is small it can be fully used. But computing with such a representation requires completely dependable nodes. In the case where the hidden nodes are noisy and unreliable, we find that error correcting schemes emerge simply by using noisy units during training; random errors injected during… CONTINUE READING

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 14 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-8 OF 8 REFERENCES

Principle and Practise of Information Theory. Reading MA, Addison Wesley

  • R E.
  • 1987
Highly Influential
4 Excerpts

A neural network classifier based on coding theory

  • Chiueh, Tz-Dar, Rodney Goodman
  • Neural Information Processing Systems,
  • 1987

Similar Papers

Loading similar papers…