Name
Abstract | ||
|---|---|---|
Standard shared-weight neural networks previously demonstrated inferior performance to that of morphological shared-weight neural networks for automatic target detection. Empirical analysis showed that entropy measures of the features generated by the standard shared-weight neural networks were consistently lower than those generated by the morphological shared-weight neural networks. Based on this observation, an entropy maximization term was added to the standard shared-weight network objective function. In this paper, we present automatic target detection results for standard shared-weight neural networks trained with and without the added entropy term |
Year | DOI | Venue |
|---|---|---|
2000 | 10.1109/72.822520 | IEEE Trans. Neural Netw. Learning Syst. |
Keywords | Field | DocType |
automatic target recognition,neural network,neural nets,kernel,mathematical morphology,object recognition,entropy,learning artificial intelligence,feature extraction,maximum entropy,morphology,neural networks,indexing terms,convolution,objective function,testing | Kernel (linear algebra),Object detection,Pattern recognition,Entropy maximization,Computer science,Feature extraction,Time delay neural network,Artificial intelligence,Deep learning,Principle of maximum entropy,Artificial neural network,Machine learning | Journal |
Volume | Issue | ISSN |
11 | 1 | 1045-9227 |
Citations | PageRank | References |
14 | 0.83 | 12 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mohamed A. Khabou | 1 | 84 | 9.90 |
| Paul Gader | 2 | 1909 | 196.70 |