TY - GEN
T1 - Multilayer feed-forward artificial neural network integrated with sensitivity based connection pruning method
AU - Urolagin, Siddhaling
AU - Prema, K. V.
AU - Jayakrishna, R.
AU - Reddy, N. V.Subba
PY - 2012/12/1
Y1 - 2012/12/1
N2 - The Artificial Neural Network (ANN) with small size may not solve the problem while the network with large size will suffer from poor generalization. The pruning methods are approaches for finding appropriate size of the network by eliminating few parameters from the network. The sensitivity based pruning will determine sensitivity of the network error for removal of a parameter and eliminate parameters with least sensitivity. In this research a sensitivity based pruning method is integrated with multilayer feed-forward ANN and applied on MNIST handwritten numeral recognition. An analysis of effect of pruning on the network is compared with performance of a network without pruning. It is observed that the network integrated with pruning method show better generalization ability than a network without pruning method being incorporated.
AB - The Artificial Neural Network (ANN) with small size may not solve the problem while the network with large size will suffer from poor generalization. The pruning methods are approaches for finding appropriate size of the network by eliminating few parameters from the network. The sensitivity based pruning will determine sensitivity of the network error for removal of a parameter and eliminate parameters with least sensitivity. In this research a sensitivity based pruning method is integrated with multilayer feed-forward ANN and applied on MNIST handwritten numeral recognition. An analysis of effect of pruning on the network is compared with performance of a network without pruning. It is observed that the network integrated with pruning method show better generalization ability than a network without pruning method being incorporated.
UR - http://www.scopus.com/inward/record.url?scp=84873946051&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84873946051&partnerID=8YFLogxK
U2 - 10.1007/978-3-642-35615-5_10
DO - 10.1007/978-3-642-35615-5_10
M3 - Conference contribution
AN - SCOPUS:84873946051
SN - 9783642356148
T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering
SP - 68
EP - 74
BT - Advances in Communication, Network, and Computing - Third International Conference, CNC 2012, Revised Selected Papers
T2 - 3rd International Conference on Advances in Communication, Network, and Computing, CNC 2012
Y2 - 24 February 2012 through 25 February 2012
ER -