Adaptive generalisation

@article{Sharkey1993AdaptiveG,
  title={Adaptive generalisation},
  author={Noel E. Sharkey and Amanda J. C. Sharkey},
  journal={Artificial Intelligence Review},
  year={1993},
  volume={7},
  pages={313-328}
}
Adaptive generalisation is the ability to use prior knowledge in the performance of novel tasks. Thus, if we are to model intelligent behaviour with neural nets, they must be able to generalise across task domains. Our objective is to elucidate the aetiology of transfer of information between connectionist nets. First, a method is described that provides a standardised score for the quantification of how much task structure a net has extracted, and to what degree knowledge has been transferred… CONTINUE READING

Figures, Tables, and Topics from this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 17 REFERENCES

Artificial Neural Networks: Approximation and Learning

  • H. 38--69. White
  • 1992

Non-Literal Transfer of Information among Inductive Learners

  • L. Y. Pratt
  • Computer
  • 1992
1 Excerpt

The Statistical Independence of Network Generalisation : An Application in Software Engineering

  • N. E. Sharkey, D. Partridge
  • 1992

Type Generalisations on Distributed Representations

  • R. Trapl
  • Cybernetics and Systems Research , 1327 - - 1334
  • 1992

Similar Papers

Loading similar papers…