Title :
A learning algorithm for multi-layer perceptron networks with nondifferentiable nonlinearities
Author :
Buhrke, Eric R. ; LoCicero, Joseph L.
Author_Institution :
Dept. of Electr. & Comput. Eng., Illinois Inst. of Technol., Chicago, IL, USA
Abstract :
A learning algorithm is proposed for neural networks with hard limiting nonlinearities. The algorithm is gradient-based, where the gradient is related to the average network response rather than to its instantaneous value. This gradient is well defined and computable. The algorithm was demonstrated on a vowel discrimination problem, where good results were achieved
Keywords :
feedforward neural nets; learning (artificial intelligence); speech recognition; learning algorithm; multi-layer perceptron; neural networks; nondifferentiable nonlinearities; vowel discrimination; Backpropagation algorithms; Computational efficiency; Feedforward neural networks; Information processing; Multi-layer neural network; Multilayer perceptrons; Neural networks; Neurons; Pattern recognition; Quantization;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.287065
