Corpus ID: 16333127

Steps Towards`self-referential' Neural Learning: a Thought Experiment

@inproceedings{Schmidhuber1992StepsTN,
  title={Steps Towards`self-referential' Neural Learning: a Thought Experiment},
  author={J. Urgen Schmidhuber},
  year={1992}
}
A major diierence between human learning and machine learning is that humans can reeect about their own learning behavior and adapt it to typical learning tasks in a given environment. To make some initial theoretical steps towardìntrospective' machine learning, I present { as a thought experiment { a `self-referential' recurrent neural network which can run and actively modify its own weight change algorithm. The network has special input units for observing its own failures and successes… Expand
5 Citations

References

SHOWING 1-10 OF 19 REFERENCES
Incremental Development of Complex Behaviors
  • 17
  • PDF
Theory Formation by Heuristic Search
  • D. Lenat
  • Computer Science
  • Artif. Intell.
  • 1983
  • 113
  • PDF
Generalization of backpropagation with application to a recurrent gas market model
  • 812
  • PDF
Shift of bias for inductive concept learning
  • 370
Quantifying Inductive Bias: AI Learning Algorithms and Valiant's Learning Framework
  • D. Haussler
  • Mathematics, Computer Science
  • Artif. Intell.
  • 1988
  • 555
  • PDF
Learning State Space Trajectories in Recurrent Neural Networks
  • 710
  • PDF
...
1
2
...