Showing cs.LGShow all
2 papers · 1 filter
cs.LG2019
Natural-Logarithm-Rectified Activation Function in Convolutional Neural Networks
Yang Liu, Jianpeng Zhang, Chao Gao +2
Activation functions play a key role in providing remarkable performance in deep neural networks, and the rectified linear unit (ReLU) is one of the most widely used activation fun…
cs.LG2018
N-fold Superposition: Improving Neural Networks by Reducing the Noise in Feature Maps
Yang Liu, Qiang Qu, Chao Gao
Considering the use of Fully Connected (FC) layer limits the performance of Convolutional Neural Networks (CNNs), this paper develops a method to improve the coupling between the c…