Differences

This shows you the differences between two versions of the page.

--- cs704r_w2019 [2019/01/07 19:05]
wingated
+++ cs704r_w2019 [2021/06/30 23:42]
@@ Line 1: / Line 1: @@
-**Applications**
-  * BERT - https://arxiv.org/abs/1810.04805
-  * Machine Theory of Mind - http://arxiv.org/pdf/1802.07740v2.pdf
-  * Video-to-Video Synthesis
-  * Video Prediction via Selective Sampling
-  * Learning to decompose & disadvantage representations for video prediction
-**GANs / unsupervised**
-  * Composing graphical models with neural networks for structured representations and fast inference https://arxiv.org/pdf/1603.06277.pdf
-  * IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis
-  * Wasserstein GAN
-  * Text adaptive GAN: Manipulating images with natural language
-**Network design**
-  * Attention is all you need
-  * Neural Ordinary Differential Equations - https://arxiv.org/pdf/1806.07366.pdf
-  * Reversible neural networks - https://arxiv.org/abs/1807.03039 - https://arxiv.org/abs/1605.08803
-**Foundations / Philosophy**
-  * Troubling trends in ML scholarship - https://arxiv.org/pdf/1807.03341
-  * A Theory of Local Learning, the Learning Channel, and the Optimality of Backpropagation - https://arxiv.org/pdf/1506.06472
-  * Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review - https://arxiv.org/pdf/1611.00740
-**RL**
-  * Curiosity-driven exploration by self-supervised prediction
-  * Diversity is all you need: Learning skills without a reward function - http://arxiv.org/pdf/1802.06070v6.pdf
-  * World Models - https://arxiv.org/pdf/1803.10122v4.pdf
-**Graph networks**
-  * Graph Neural Networks: A Review of Methods and Applications - https://arxiv.org/abs/1812.08434
-  * Relational inductive biases, deep learning, and graph networks - https://arxiv.org/pdf/1806.01261
-**Optimization / training**
-  * Averaging weights leads to wider optima and better generalization - http://arxiv.org/pdf/1803.05407v2.pdf
-  * The loss surface of multilayer networks - https://arxiv.org/pdf/1412.0233
-  * Visualizing The Loss Landscape of Neural Nets - https://arxiv.org/pdf/1712.09913v3.pdf
-  * The Matrix Calculus You Need For Deep Learning - https://arxiv.org/pdf/1802.01528v3.pdf
-  * Group Norm - https://arxiv.org/pdf/1803.08494v3.pdf
-  * Kalman Normalization: Normalizing internal representations across network layers
-  * MetaReg: towards Domain Generalization using meta-regularization
-  * AutoAugment - https://arxiv.org/abs/1805.09501
-  * A Disciplined Approach To Neural Network Hyper-Parameters: part 1 - http://arxiv.org/pdf/1803.09820v2.pdf
-  * (Direct) Feedback alignment
-** Geometric deep learning **
-  * Geometric deep learning: going beyond Euclidean data- https://arxiv.org/pdf/1611.08097.pdf
-  * Convolutional Neural Networks on Surfaces via Seamless Toric Covers
-  * SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
-  * Deriving Neural Architectures from Sequence and Graph Kernels
-  * CayleyNets: Graph convolutional neural networks with complex rational spectral filters
-  * Deep Functional Maps: Structured Prediction for Dense Shape Correspondence
-  * Geometric matrix completion with recurrent multi-graph neural networks
-  * Neural Message Passing for Quantum Chemistry
-  * Deep Learning on Lie Groups for Skeleton-based Action Recognition
-**Other**
-  * Bayesian neural networks?

BYU CS classes

User Tools

Site Tools

Differences

Page Tools