Abstract | ||
---|---|---|
The human vision system usually has a specifically activated area of neurons when recognizing a category of images. Inspired by this visual mechanism, we propose a layerwise class-aware convolutional neural network architecture to explicitly discover category-tailored neurons on intermediate hidden layers to improve the network learning ability. Instead of directly selecting activated neurons for ... |
Year | DOI | Venue |
---|---|---|
2017 | 10.1109/TCSVT.2016.2587389 | IEEE Transactions on Circuits and Systems for Video Technology |
Keywords | Field | DocType |
Machine learning,Biological neural networks,Training,Mutual information,Computer architecture,Computational modeling,Convolutional codes | Neocognitron,Convolutional code,Pattern recognition,Computer science,Convolutional neural network,Time delay neural network,Artificial intelligence,Mutual information,Deep learning,Classifier (linguistics),Subnetwork | Journal |
Volume | Issue | ISSN |
27 | 12 | 1051-8215 |
Citations | PageRank | References |
0 | 0.34 | 20 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhen Cui | 1 | 580 | 41.43 |
Zhiheng Niu | 2 | 52 | 3.50 |
Luoqi Liu | 3 | 397 | 18.64 |
Shuicheng Yan | 4 | 9701 | 359.54 |