Explanation-Based Neural Network Learning for Robot Control

  title={Explanation-Based Neural Network Learning for Robot Control},
  author={Tom M. Mitchell and Sebastian Thrun},
How can artificial neural nets generalize better from fewer examples? In order to generalize successfully, neural network learning methods typically require large training data sets. We introduce a neural network learning method that generalizes rationally from many fewer data points, relying instead on prior knowledge encoded in previously learned neural networks. For example, in robot control learning tasks reported here, previously learned networks that model the effects of robot actions are… CONTINUE READING
68 Citations
17 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 17 references

Tangent prop

  • Simard et al, 1992 Patrice Simard, Bernard Victorri, Yann LeCun, John Denker
  • 1992

Real - time learning and control using asynchronous dynamic programming

  • Andy G. Barto, StevenJ. Bradtke, Satinder P. Singh
  • 1991
1 Excerpt

An approach to combining

  • Shavlik, Towell, 1989 Jude W. Shavlik, G. G. Towell
  • 1989

An approach to combining explanationbased and neural learning algorithms

  • G. G. Towell
  • Connection Science
  • 1989
1 Excerpt

Similar Papers

Loading similar papers…