Natural deduction is essentially a sequential decision task, similar to many game-playing tasks. Such a task is well suited to benefit from the techniques of neuro-evolution. Symbiotic, Adaptive Neuro-Evolution (SANE; Moriarty and Miikkulainen 1996) has proven successful at evolving networks for such tasks. This paper will show that SANE can be used to evolve a natural deduction system on a neural network. Particularly, it will show that (1) incremental evolution through progressively more challenging problems results in more effective networks than does direct evolution, and (2) an effective network can be evolved faster if the network is allowed to brainstorm'' or suggest any move regardless of its applicability, even though the highest-ranked valid move is always applied. This way evolution results in neural networks with human-like reasoning behavior.

PDF, PS

In Proceedings of The First {IEEE} Symposium on Combinations of Evolutionary Computation and Neural Networks, pp. 64-69, Piscataway, NJ 2000. IEEE.

@InProceedings{desai:ecnn00, title={Neuro-Evolution And Natural Deduction}, author={Nirav S. Desai and Risto Miikkulainen}, booktitle={Proceedings of The First {IEEE} Symposium on Combinations of Evolutionary Computation and Neural Networks}, address={Piscataway, NJ}, publisher={IEEE}, pages={64-69}, url="http://www.cs.utexas.edu/users/ai-lab?desai:ecnn00", year={2000} }