Learnability and the Vapnik-Chervonenkis dimension
Journal of the ACM (JACM)
Symbolic-neural systems and the use of hints for developing complex systems
International Journal of Man-Machine Studies
Neural Computation
The nature of statistical learning theory
The nature of statistical learning theory
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
A Method for Learning From Hints
Advances in Neural Information Processing Systems 5, [NIPS Conference]
Does extra knowledge necessarily improve generalization?
Neural Computation
Incorporating prior model into Gaussian processes regression for WEDM process modeling
Expert Systems with Applications: An International Journal
Training without data: knowledge insertion into RBF neural networks
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
Hi-index | 0.00 |
The incorporation of prior knowledge into neural networks can improve neural network learning in several respects, for example, a faster learning speed and better generalizationability. However, neural network learning is data driven andthere is no general way to exploit knowledge which is not in the formof data input-output pairs. In this paper, we propose two approaches forincorporating knowledge into neural networks from fuzzyrules. These fuzzy rules are generated based on expert knowledge orintuition. In the first approach, information from the derivative ofthe fuzzy system is used to regularize the neural network learning,whereas in the second approach the fuzzy rules are used as a catalyst.Simulation studies show that both approaches increasethe learning speed significantly.