Name
Abstract | ||
|---|---|---|
The neural network with optimal architecture speeds up the learning process and generalizes the problem well for further knowledge extraction. As a result researchers have developed various techniques for pruning the neural networks. This paper provides a survey of existing pruning techniques that optimize the architecture of neural networks and discusses their advantages and limitations. Also the paper evaluates the effectiveness of various pruning techniques by comparing the performance of some traditional and recent pruning algorithms based on sensitivity analysis, mutual information and significance on four real datasets namely Iris, Wisconsin breast cancer, Hepatitis Domain and Pima Indian Diabetes. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.2478/s13537-013-0109-x | Central Europ. J. Computer Science |
Keywords | Field | DocType |
input and hidden neurons pruning, optimization techniques, classification, feedforward neural networks, data mining | Data mining,Feedforward neural network,Computer science,Algorithm,Knowledge extraction,Artificial intelligence,Mutual information,Pruning (decision trees),Artificial neural network,Pima Indian,Machine learning,Pruning | Journal |
Volume | Issue | ISSN |
3 | 3 | 2299-1093 |
Citations | PageRank | References |
12 | 0.54 | 32 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| M. Gethsiyal Augasta | 1 | 56 | 3.01 |
| T. Kathirvalavakumar | 2 | 88 | 5.75 |