Title :
Optimal pruning of neural tree networks for improved generalization
Author :
Sankar, Ananth ; Mammone, Richard J.
Author_Institution :
Dept. of Electr. Eng., Rutgers Univ., Piscataway, NJ, USA
Abstract :
An optimal pruning algorithm for neural tree networks (NTN) is presented. The NTN is grown by a constructive learning algorithm that decreases the classification error on the training data recursively. The optimal pruning algorithm is then used to improve generalization. The pruning algorithm is shown to be computationally inexpensive. Simulation results on a speaker-independent vowel recognition task are presented to show the improved generalization using the pruning algorithm
Keywords :
neural nets; optimisation; speech recognition; trees (mathematics); classification error; constructive learning algorithm; generalization; neural tree networks; optimal pruning; speaker-independent vowel recognition; speech recognition; training data; Backpropagation algorithms; Binary trees; Classification algorithms; Classification tree analysis; Feedforward neural networks; Neural networks; Neurons; Speech recognition; Training data; Tree data structures;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155341
