Soft sensors that can discriminate shear and normal force could help pro...
The posterior collapse phenomenon in variational autoencoders (VAEs), wh...
Modern deep neural networks have achieved superhuman performance in task...
Graph Neural Networks (GNNs) had been demonstrated to be inherently
susc...
Generative Flow Networks (GFlowNets) are recently proposed models for
le...
Transformers have achieved remarkable success in sequence modeling and b...
Multi-head attention empowers the recent success of transformers, the
st...
Medical image segmentation has been so far achieving promising results w...
Medical image analysis using deep learning has recently been prevalent,
...
We present and review an algorithmic and theoretical framework for impro...
Neural networks are vulnerable to input perturbations such as additive n...
We study sample complexity of optimizing "hill-climbing friendly" functi...
The problem of learning an optimal convex combination of basis models ha...
Out-of-distribution (OoD) detection is a natural downstream task for dee...
State-of-the-art convolutional neural networks (CNNs) yield record-break...
Unsupervised and semi-supervised learning are important problems that ar...
Semi-supervised learning algorithms reduce the high cost of acquiring la...
We develop a probabilistic framework for deep learning based on the Deep...
In this paper we introduce a block-structured adaptive mesh refinement (...
A grand challenge in machine learning is the development of computationa...