Home /
Research
Showing 193 - 198 / 897
KD-Lib: A PyTorch library for Knowledge Distillation, Pruning and Quantization
HetShah, AvishreeKhare, NeelayShah....
Published date-11/30/2020
ModelCompression, Quantization
In recent years, the growing size of neural networks has led to a vast amount of research concerning compression techniques to mitigate the drawbacks of such large sizes. Most of …
Optimizing the Neural Architecture of Reinforcement Learning Agents
N.Mazyavkina, S.Moustafa, I.Trofimov....
Published date-11/30/2020
NeuralArchitectureSearch
Reinforcement learning (RL) enjoyed significant progress over the last years. One of the most important steps forward was the wide application of neural networks. However, architectures of these neural networks …
Doubly Stochastic Subspace Clustering
DerekLim, RenéVidal, BenjaminD.Haeffele....
Published date-11/30/2020
Clustering, ImageClustering
Many state-of-the-art subspace clustering methods follow a two-step process by first constructing an affinity matrix between data points and then applying spectral clustering to this affinity. Most of the research …
Deep Implicit Templates for 3D Shape Representation
ZerongZheng, TaoYu, QionghaiDai....
Published date-11/30/2020
3DShapeRepresentation
Deep implicit functions (DIFs), as a kind of 3D shape representation, are becoming more and more popular in the 3D vision community due to their compactness and strong representation power. …
General Invertible Transformations for Flow-based Generative Modeling
JakubM.Tomczak....
Published date-11/30/2020
In this paper, we present a new class of invertible transformations. We indicate that many well-known invertible tranformations in reversible logic and reversible neural networks could be derived from our …
Large-Scale Gravitational Lens Modeling with Bayesian Neural Networks for Accurate and Precise Inference of the Hubble Constant
JiWonPark, SebastianWagner-Carena, SimonBirrer....
Published date-11/30/2020
We investigate the use of approximate Bayesian neural networks (BNNs) in modeling hundreds of time-delay gravitational lenses for Hubble constant ($H_0$) determination. Our BNN was trained on synthetic HST-quality images …