Deep Learning
On the universality of deep learning Emmanuel Abbe Mathematics Institute EPFL Lausanne, 1005 Switzerland Colin Sandon Department of Mathematics MIT Cambridge, MA02139
This paper shows that deep learning, i.e., neural networks trained by SGD, can learn
MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation
Video prediction is a challenging task.
DropGNN: Random Dropouts Increase the Expressiveness of Graph Neural Networks
Then, we combine the results of these runs to obtain the final result. We prove that DropGNNs can distinguish various graph neighborhoods that cannot be separated by message passing GNNs.
Decomposing NeRF for Editing via Feature Field Distillation
Emerging neural radiance fields (NeRF) are a promising scene representation for computer graphics, enabling high-quality 3D reconstruction and novel view synthesis from image observations.
Learning rule influences recurrent network representations but not attractor structure in decision-making tasks
RNN computation is valuable in two ways.
MaskTune: Mitigating Spurious Correlations by Forcing to Explore
This work proposes MaskTune, a masking strategy that prevents over-reliance on spurious (or a limited number of) features.
Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks
This paper provides a simple explanation for why batch normalized deep residual networks are easily trainable.