Multilayer feedforward networks are universal approximators
Neural Networks
Speech Communication - Special issue on robust speech recognition
Representation properties of networks: Kolmogorov's theorem is irrelevant
Neural Computation
Hi-index | 0.00 |
Some well known theoretical results concerning the universal approximation property of MLP neural networks with one hidden layer have shown that for any function f from [0, 1]n to R, only the output layer weights depend on f. We use this result to propose a network architecture called the predictive Kohonen map allowing to design a new speech features extractor. We give experimental results of this approach on a phonemes recognition task.