Abstract | ||
---|---|---|
Convolutional Neural Network (CNN) is a very popular and powerful machine learning technique for image classification. The performance of image classification depends on CNN's untangling ability of the entangled high-dimensional input data, which can be measured by the linear separability of the output vectors in the last fully-connected (fc) layer of the CNN. Inspired by the neural population coding of inferotemporal (IT) cortex in brain, we proposed a brain-inspired method named predropout & inhibition for better restricting the coding patterns and making them with lower energy and higher sparseness. The proposed predropout & inhibition method can 1) largely reduce the number of connections from the last fc layer to softmax layer, 2) restrict the energy of coding patterns at a low level significantly, and 3) improve classification performance on ImageNet-20 significantly. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/CISP-BMEI.2018.8633220 | CISP-BMEI |
Keywords | Field | DocType |
Encoding,Neurons,Training,Convolutional codes,Image coding,Image classification,Visualization | Linear separability,Convolutional code,Pattern recognition,Softmax function,Computer science,Neural coding,Convolutional neural network,Coding (social sciences),Artificial intelligence,Contextual image classification,Encoding (memory) | Conference |
ISBN | Citations | PageRank |
978-1-5386-7604-2 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wenjie Chen | 1 | 7 | 7.46 |
Fengtong Du | 2 | 2 | 1.38 |
Ye Wang | 3 | 0 | 0.34 |
Lihong Cao | 4 | 59 | 3.65 |