5 papers
Refining the Information Bottleneck via Adversarial Information Separation
Shuai Ning, Zhenpeng Wang, Lin Wang +5
Generalizing from limited data is particularly critical for models in domains such as material science, where task-relevant features in experimental datasets are often heavily conf…
Convolution-Based Converter : A Weak-Prior Approach For Modeling Stochastic Processes Based On Conditional Density Estimation
Chaoran Pang, Lin Wang, Shuangrong Liu +4
In this paper, a Convolution-Based Converter (CBC) is proposed to develop a methodology for removing the strong or fixed priors in estimating the probability distribution of target…
Disentanglement in Difference: Directly Learning Semantically Disentangled Representations by Maximizing Inter-Factor Differences
Xingshen Zhang, Lin Wang, Shuangrong Liu +3
In this study, Disentanglement in Difference(DiD) is proposed to address the inherent inconsistency between the statistical independence of latent variables and the goal of semanti…
OPT-GAN: A Broad-Spectrum Global Optimizer for Black-box Problems by Learning Distribution
Minfang Lu, Shuai Ning, Shuangrong Liu +4
Black-box optimization (BBO) algorithms are concerned with finding the best solutions for problems with missing analytical details. Most classical methods for such problems are bas…
Improving Neural Network Classifier using Gradient-based Floating Centroid Method
Mazharul Islam, Shuangrong Liu, Lin Wang +1
Floating centroid method (FCM) offers an efficient way to solve a fixed-centroid problem for the neural network classifiers. However, evolutionary computation as its optimization m…