Deep Learning
TorsionNet: A Reinforcement Learning Approach to Sequential Conformer Search
Molecular geometry prediction of flexible molecules, or conformer search, is a longstanding challenge in computational chemistry.
Black-Box Ripper: Copying black-box models using generative evolutionary algorithms Antonio B arb al au
In this context, we present a teacher-student framework that can distill the black-box (teacher) model into a student model with minimal accuracy loss.
Meta-Auto-Decoder for Solving Parametric Partial Differential Equations
Another category of methods such as Fourier Neural Operator (FNO) and Deep Operator Network (DeepONet) try to approximate the solution mapping directly.
Ultrahyperbolic Neural Networks
We experimentally show the relevance of our approach in the tasks of graph and node classification.
MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation
The vision community has rapidly improved image synthesis results on quality, diversity and resolution over a short period of time.
4 Proofs of positive results: universality of deep learning 4.1 Emulation of arbitrary algorithms
We then train a neural network to learn the parity label of these images with a random initalization.
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.