Learning internal representations by error propagation
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Adaptation and Learning in Automatic Systems
Adaptation and Learning in Automatic Systems
Design of time delay neural networks for speech recognition
Design of time delay neural networks for speech recognition
| Hi-index | 0.00 |
This paper describes a new learning algorithm for the multi-layer perceptron. The learning problem is stated formally as an optimization problem that is solved through a series of systematic approximations. The solution uses the moments of the training data to design the network. This procedure has several advantages, most importantly is the reduction in training time. The algorithm is verified and compared to backpropagation. In a speech recognition experiment the total training time was reduced by more than 75% when compared to backpropagation.