This is mostly my reading dump. They are too deep to post at [AIDL], but it's interesting enough for me to take some notes. Putting all notes at git is a habit I learned from Denny Britz.
Highlight:
- A Neural Algorithm of Artistic Style [arXiv]
- Semantic Style Transfer and Turning Two-Bit Doodles into Fine Artworks, by Alex J. Champandard [arXiv]
Interesting:
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution
- Style Transfer via Texture Synthesis by Michael Elad and Peyman Milanfar [IEEE]
- Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis [arXiv]
- Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network [arXiv]
- https://github.com/alexjc/neural-enhance
- https://en.wikipedia.org/wiki/Bicubic_interpolation
- https://blog.openai.com/generative-models/
- Improved Techniques for Training GANs [arXiv]
- Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World [arXiv]
- Pixel Recurrent Neural Networks [arXiv]
- A guide to convolution arithmetic for deep learning [arXiv]
Highlight:
- Simultaneous Detection and Segmentation [arXiv]
- Wasserstein GAN [arXiv]
- FeUdal Networks for Hierarchical Reinforcement Learning [arXiv]
- Skip-Thought Vectors [arXiv]
- Evolution StMichael Elad and Peyman Milanfar rategies as a Scalable Alternative to Reinforcement Learning [arXiv]
Interesting:
- Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis [arXiv]
- On the Behavior of Convolutional Nets for Feature Extraction [arXiv]
- Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning [arXiv]
- Accelerated Gradient Temporal Difference Learning [arXiv]]
- Fast LIDAR-based Road Detection Using Convolutional Neural Networks [arXiv]
- Deep Robust Kalman Filter arXiv
- Deep Learning applied to NLP arXiv
- Deep Reinforcement Learning: AN OVERVIEW https://arxiv.org/pdf/1701.07274.pdf