2 papers
cs.LG2020
Effects of the Nonlinearity in Activation Functions on the Performance of Deep Learning Models
Nalinda Kulathunga, Nishath Rajiv Ranasinghe, Daniel Vrinceanu +3
The nonlinearity of activation functions used in deep learning models are crucial for the success of predictive models. There are several commonly used simple nonlinear functions,…
cs.CV2018
Utilizing Complex-valued Network for Learning to Compare Image Patches
Siwen Jiang, Wenxuan Wei, Shihao Guo +2
At present, the great achievements of convolutional neural network(CNN) in feature and metric learning have attracted many researchers. However, the vast majority of deep network a…