activity
20182021
most citedA synthetic dataset for deep learning

3 citations · 10 across the 5 of their papers we have counts for

collaborators

7 papers

cs.LG20212 cited

A Probabilistic Representation of DNNs: Bridging Mutual Information and Generalization

Xinjie Lan, Kenneth Barner

Recently, Mutual Information (MI) has attracted attention in bounding the generalization error of Deep Neural Networks (DNNs). However, it is intractable to accurately estimate the…

cs.LG20202 cited

A Probabilistic Representation of Deep Learning for Improving The Information Theoretic Interpretability

Xinjie Lan, Kenneth E. Barner

In this paper, we propose a probabilistic representation of MultiLayer Perceptrons (MLPs) to improve the information-theoretic interpretability. Above all, we demonstrate that the…

cs.LG20202 cited

PAC-Bayesian Generalization Bounds for MultiLayer Perceptrons

Xinjie Lan, Xin Guo, Kenneth E. Barner

We study PAC-Bayesian generalization bounds for Multilayer Perceptrons (MLPs) with the cross entropy loss. Above all, we introduce probabilistic explanations for MLPs in two aspect…

cs.LG20191 cited

Explicitly Bayesian Regularizations in Deep Learning

Xinjie Lan, Kenneth E. Barner

Generalization is essential for deep learning. In contrast to previous works claiming that Deep Neural Networks (DNNs) have an implicit regularization implemented by the stochastic…

cs.LG2019

A Probabilistic Representation of Deep Learning

Xinjie Lan, Kenneth E. Barner

In this work, we introduce a novel probabilistic representation of deep learning, which provides an explicit explanation for the Deep Neural Networks (DNNs) in three aspects: (i) n…

cs.CV20193 cited

A synthetic dataset for deep learning

Xinjie Lan

In this paper, we propose a novel method for generating a synthetic dataset obeying Gaussian distribution. Compared to the commonly used benchmark datasets with unknown distributio…