X
Xia Hu
Researcher at Simon Fraser University
Publications - 8
Citations - 192
Xia Hu is an academic researcher from Simon Fraser University. The author has contributed to research in topics: Piecewise linear function & Artificial neural network. The author has an hindex of 3, co-authored 8 publications receiving 83 citations.
Papers
More filters
Proceedings ArticleDOI
Exact and Consistent Interpretation for Piecewise Linear Neural Networks: A Closed Form Solution
TL;DR: In this paper, the authors propose an elegant closed form solution named $OpenBox$ to compute exact and consistent interpretations for the family of piecewise linear neural networks (PLNN).
Journal ArticleDOI
Model complexity of deep learning: a survey
TL;DR: In this article, the authors conduct a systematic overview of the latest studies on model complexity in deep learning and propose several interesting future directions, including model generalization, model optimization, and model selection and design.
Posted Content
Measuring Model Complexity of Neural Networks with Curve Activation Functions
TL;DR: This paper proposes linear approximation neural network (LANN), a piecewise linear framework to approximate a given deep model with curve activation function, and proposes two approaches to prevent overfitting by directly constraining model complexity, namely neuron pruning and customized L1 regularization.
Proceedings ArticleDOI
Measuring Model Complexity of Neural Networks with Curve Activation Functions
TL;DR: Linear approximation neural networks (LANN) as discussed by the authors constructs individual piecewise linear approximation for the activation function of each neuron, and minimizes the number of linear regions to satisfy a required approximation degree.
Proceedings ArticleDOI
Exact and Consistent Interpretation of Piecewise Linear Models Hidden behind APIs: A Closed Form Solution
TL;DR: An elegant closed form solution named OpenAPI is proposed to compute exact and consistent interpretations for the family of Piecewise Linear Models (PLM), which includes many popular classification models.