research
∙
01/16/2023
Data-aware customization of activation functions reduces neural network error
Activation functions play critical roles in neural networks, yet current...
share
research
∙
01/16/2023
Ae^2I: A Double Autoencoder for Imputation of Missing Values
The most common strategy of imputing missing values in a table is to stu...
research
∙
02/16/2021
Predicting Material Properties Using a 3D Graph Neural Network with Invariant Local Descriptors
Accurately predicting material properties is critical for discovering an...
research
∙
11/23/2020
A Use of Even Activation Functions in Neural Networks
Despite broad interest in applying deep learning techniques to scientifi...
research
∙
06/03/2020