This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
cs704r_w2019 [2019/01/07 19:03] wingated |
cs704r_w2019 [2021/06/30 23:42] (current) |
||
---|---|---|---|
Line 8: | Line 8: | ||
**GANs / unsupervised** | **GANs / unsupervised** | ||
- | IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis | + | * Composing graphical models with neural networks for structured representations and fast inference https://arxiv.org/pdf/1603.06277.pdf |
- | Wasserstein GAN | + | * IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis |
- | Text adaptive GAN: Manipulating images with natural language | + | * Wasserstein GAN |
+ | * Text adaptive GAN: Manipulating images with natural language | ||
**Network design** | **Network design** | ||
- | Attention is all you need | + | * Attention is all you need |
- | Neural Ordinary Differential Equations - https://arxiv.org/pdf/1806.07366.pdf | + | * 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 | + | * Reversible neural networks - https://arxiv.org/abs/1807.03039 - https://arxiv.org/abs/1605.08803 |
| | ||
**Foundations / Philosophy** | **Foundations / Philosophy** | ||
- | Troubling trends in ML scholarship - https://arxiv.org/pdf/1807.03341 | + | * 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 | + | * 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 | + | * Why and When Can Deep -- but Not Shallow -- Networks Avoid the Curse of Dimensionality: a Review - https://arxiv.org/pdf/1611.00740 |
| | ||
**RL** | **RL** | ||
- | Curiosity-driven exploration by self-supervised prediction | + | * 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 | + | * 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 | + | * World Models - https://arxiv.org/pdf/1803.10122v4.pdf |
**Graph networks** | **Graph networks** | ||
- | Graph Neural Networks: A Review of Methods and Applications - https://arxiv.org/abs/1812.08434 | + | * 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 | + | * Relational inductive biases, deep learning, and graph networks - https://arxiv.org/pdf/1806.01261 |
**Optimization / training** | **Optimization / training** | ||
- | Averaging weights leads to wider optima and better generalization - http://arxiv.org/pdf/1803.05407v2.pdf | + | * 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 | + | * 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 | + | * 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 | + | * The Matrix Calculus You Need For Deep Learning - https://arxiv.org/pdf/1802.01528v3.pdf |
- | Group Norm - https://arxiv.org/pdf/1803.08494v3.pdf | + | * Group Norm - https://arxiv.org/pdf/1803.08494v3.pdf |
- | Kalman Normalization: Normalizing internal representations across network layers | + | * Kalman Normalization: Normalizing internal representations across network layers |
- | MetaReg: towards Domain Generalization using meta-regularization | + | * MetaReg: towards Domain Generalization using meta-regularization |
- | AutoAugment - https://arxiv.org/abs/1805.09501 | + | * AutoAugment - https://arxiv.org/abs/1805.09501 |
- | A Disciplined Approach To Neural Network Hyper-Parameters: part 1 - http://arxiv.org/pdf/1803.09820v2.pdf | + | * A Disciplined Approach To Neural Network Hyper-Parameters: part 1 - http://arxiv.org/pdf/1803.09820v2.pdf |
- | (Direct) Feedback alignment | + | * (Direct) Feedback alignment |
** Geometric deep learning ** | ** Geometric deep learning ** | ||
- | Geometric deep learning: going beyond Euclidean data- https://arxiv.org/pdf/1611.08097.pdf | + | * Geometric deep learning: going beyond Euclidean data- https://arxiv.org/pdf/1611.08097.pdf |
- | Convolutional Neural Networks on Surfaces via Seamless Toric Covers | + | * Convolutional Neural Networks on Surfaces via Seamless Toric Covers |
- | SchNet: A continuous-filter convolutional neural network for modeling quantum interactions | + | * SchNet: A continuous-filter convolutional neural network for modeling quantum interactions |
- | Deriving Neural Architectures from Sequence and Graph Kernels | + | * Deriving Neural Architectures from Sequence and Graph Kernels |
- | CayleyNets: Graph convolutional neural networks with complex rational spectral filters | + | * CayleyNets: Graph convolutional neural networks with complex rational spectral filters |
- | Deep Functional Maps: Structured Prediction for Dense Shape Correspondence | + | * Deep Functional Maps: Structured Prediction for Dense Shape Correspondence |
- | Geometric matrix completion with recurrent multi-graph neural networks | + | * Geometric matrix completion with recurrent multi-graph neural networks |
- | Neural Message Passing for Quantum Chemistry | + | * Neural Message Passing for Quantum Chemistry |
- | Deep Learning on Lie Groups for Skeleton-based Action Recognition | + | * Deep Learning on Lie Groups for Skeleton-based Action Recognition |
| | ||
**Other** | **Other** | ||
- | Bayesian neural networks? | + | * Bayesian neural networks? |