TY - GEN
T1 - Pruning strategies for the MTiling constructive learning algorithm
AU - Parekh, R.
AU - Tang, J.
AU - Honavar, V.
PY - 1997
Y1 - 1997
N2 - We present a framework for incorporating pruning strategies in the MTiling constructive neural network learning algorithm. Pruning involves elimination of redundant elements (connection weights or neurons) from a network and is of considerable practical interest. We describe three elementary sensitivity based strategies for pruning neurons. Experimental results demonstrate a moderate to significant reduction in the network size without compromising the network's generalization performance.
AB - We present a framework for incorporating pruning strategies in the MTiling constructive neural network learning algorithm. Pruning involves elimination of redundant elements (connection weights or neurons) from a network and is of considerable practical interest. We describe three elementary sensitivity based strategies for pruning neurons. Experimental results demonstrate a moderate to significant reduction in the network size without compromising the network's generalization performance.
UR - http://www.scopus.com/inward/record.url?scp=0030682698&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0030682698&partnerID=8YFLogxK
U2 - 10.1109/ICNN.1997.614199
DO - 10.1109/ICNN.1997.614199
M3 - Conference contribution
AN - SCOPUS:0030682698
SN - 0780341228
SN - 9780780341227
T3 - IEEE International Conference on Neural Networks - Conference Proceedings
SP - 1960
EP - 1965
BT - 1997 IEEE International Conference on Neural Networks, ICNN 1997
T2 - 1997 IEEE International Conference on Neural Networks, ICNN 1997
Y2 - 9 June 1997 through 12 June 1997
ER -