Deep Learning Theory
-
Revisiting Weight Initialization of Deep Neural Networks
Maciej Skorski (University of Luxembourg)*; Martin Theobald (University of Luxembourg); Alessandro. Temperoni (University of Luxembourg) -
Understanding How Over-Parametrization Leads to Acceleration: A case of learning a single teacher neuron
Jun-Kun Wang (Yale University)*; Jacob D Abernethy (Georgia Institute of Technolog) -
Towards Interpreting Deep Neural Networks via Layer Behavior Understanding
Jiezhang Cao (South China University of Technology); Jincheng Li (South China University of Technology); Xiping Hu (Lanzhou University); Xiangmiao Wu (SCUT); Mingkui Tan (South China University of Technology)* -
Ensembling With a Fixed Parameter Budget: When Does It Help and Why?
Didan Deng (Hong Kong University of Science and Technology)*; Bertram E Shi (ECE Department of Hong Kong University of Science and Technology) -
Layer-Wise Neural Network Compression via Layer Fusion
James T O' Neill (University of Liverpool)*; Aram Galstyan (USC Information Sciences Institute); Greg Ver Steeg (USC Information Sciences Institute) -
Multi-factor Memory Attentive Model for Knowledge Tracing
Liu Congjie (Liaoning University); Xiaoguang Li (Liaoning University)* -
SPDE-Net: Neural Network based prediction of stabilization parameter for SUPG technique
Sangeeta Yadav (Indian Institute of Science)*; Sashikumaar Ganesan (Indian Institute of Science)