23 citations · 44 across the 13 of their papers we have counts for
13 papers
Data-aware customization of activation functions reduces neural network error
Fuchang Gao, Boyu Zhang
Activation functions play critical roles in neural networks, yet current off-the-shelf neural networks pay little attention to the specific choice of activation functions used. Her…
: A Double Autoencoder for Imputation of Missing Values
Fuchang Gao
The most common strategy of imputing missing values in a table is to study either the column-column relationship or the row-row relationship of the data table, then use the relatio…
Predicting Material Properties Using a 3D Graph Neural Network with Invariant Local Descriptors
Boyu Zhang, Mushen Zhou, Jianzhong Wu +1
Accurate prediction of physical properties is critical for discovering and designing novel materials. Machine learning technologies have attracted significant attention in the mate…
A Use of Even Activation Functions in Neural Networks
Fuchang Gao, Boyu Zhang
Despite broad interest in applying deep learning techniques to scientific discovery, learning interpretable formulas that accurately describe scientific data is very challenging be…
Convex Regression in Multidimensions: Suboptimality of Least Squares Estimators
Gil Kur, Fuchang Gao, Adityanand Guntuboyina +1
Under the usual nonparametric regression model with Gaussian errors, Least Squares Estimators (LSEs) over natural subclasses of convex functions are shown to be suboptimal for esti…
Upper tail probabilities of integrated Brownian motions
Fuchang Gao, Xiangfeng Yang
We obtain new upper tail probabilities of -times integrated Brownian motions under the uniform norm and the norm. For the uniform norm, Talagrand's approach is used, while…