3 papers
stat.ML2026
Interpreting FCDNNs via RG on Exponential Family
Fuzhou Gong, Zigeng Xia
We consider establishing the interpretability theory of deep learning through constructing a corresponding relationship between the renormalization group (RG) method in statistical…
cond-mat.dis-nn2022
Interpreting Deep Learning by Establishing a Rigorous Corresponding Relationship with Renormalization Group
Fuzhou Gong, Zigeng Xia
In this paper, we focus on the interpretability of deep neural network. Our work is motivated by the renormalization group (RG) in statistical mechanics. RG plays the role of a bri…
cs.LG2018
Generate the corresponding Image from Text Description using Modified GAN-CLS Algorithm
Fuzhou Gong, Zigeng Xia
Synthesizing images or texts automatically is a useful research area in the artificial intelligence nowadays. Generative adversarial networks (GANs), which are proposed by Goodfell…