activity
20152022
most citedA Confident Information First Principle for Parametric Reduction and Model Selection of Boltzmann Machines

1 citations · 1 across the 2 of their papers we have counts for

collaborators

6 papers

cs.CL2022

Aligning Recommendation and Conversation via Dual Imitation

Jinfeng Zhou, Bo Wang, Minlie Huang +4

Human conversations of recommendation naturally involve the shift of interests which can align the recommendation actions and conversation process to make accurate recommendations…

cs.LG2020

Label-Based Diversity Measure Among Hidden Units of Deep Neural Networks: A Regularization Method

Chenguang Zhang, Yuexian Hou, Dawei Song +2

Although the deep structure guarantees the powerful expressivity of deep networks (DNNs), it also triggers serious overfitting problem. To improve the generalization capacity of DN…

cs.CL2019

A Tensorized Transformer for Language Modeling

Xindian Ma, Peng Zhang, Shuai Zhang +4

Latest development of neural models has connected the encoder and decoder through a self-attention mechanism. In particular, Transformer, which is solely based on self-attention, h…

quant-ph2019

Quantum observation scheme universally identifying causalities from correlations

Chenguang Zhang, Yuexian Hou, Dawei Song

It has long been recognized as a difficult problem to determine whether the observed statistical correlation between two classical variables arise from causality or from common cau…

quant-ph2018

Discrimination Between Quantum Common Causes and Quantum Causality

Mingdi Hu, Yuexian Hou

In classic cases, Reichenbach's principle implies that discriminating between common causes and causality is unprincipled since the discriminative results essentially depend on the…

cs.LG20151 cited

A Confident Information First Principle for Parametric Reduction and Model Selection of Boltzmann Machines

Xiaozhao Zhao, Yuexian Hou, Dawei Song +1

Typical dimensionality reduction (DR) methods are often data-oriented, focusing on directly reducing the number of random variables (features) while retaining the maximal variation…