README-old.md

MoDeep Seminar-Paper-Lists

Deep Learning Basics

1. Adam: A Method for Stochastic Optimization - Kingma et al.
2. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift - Sergey et al.

CNN / Image Recognition Models

1. Visualizing and Understanding Convolutional Networks - Matthew et al.
2. Going Deeper with Convolutions - Szegedy et al.
3. Rethinking the Inception Architecture for Computer Vision - Szegedy et al.
4. Deep Residual Learning for Image Recognition - Kaiming et al.
5. ImageNet Classification with Deep Convolutional Neural Networks - Krizhevsky et al.
6. Rethinking the Inception Architecture for Computer Vision
7. Dynamic Routing Between Capsules - Sabour et al.
8. Deep Visual-Semantic Alignments for Generating Image Descriptions - Karpathy et al.
9. Spatial Transformer Networks - Max Jaderberg et al.

Style Transfer

1. Understanding Deep Image Representations by Inverting Them - Mahendran
2. A Neural Algorithm of Artistic Style - Gatys

Object Detection Models

1. Faster R-CNN: Towards Real-Time Onject Detection with Region Proposal Networks - Shaoqing et al.
2. You Only Look Once: Unified, Real-Time Object Detection, YOLO - Redmon et al.
3. Fully Convolutional Networks for Semantic Segmentation - Long et al.
4. SSD: Single Shot Multibox Detector - Liu et al.
5. Deformable Convolutional Network - Dai et al.
6. Mask R-CNN - He et al.
7. Light-Head R-CNN: In Defense of Two-Stage Object Detector - Li et al.
8. Focal Loss for Dense Object Detection - Lin et al.
9. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications - Howard et al.

Generative Models

1. Auto-Encoding Variational Bayes - Kingma et al.
2. Generative Adversarial Nets - Goodfellow et al.
3. Deep Convolutional Generative Adversarial Networks - Alec et al.
4. Conditional Generative Adversarial Nets - Mehdi et al.
5. InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets - Chen et al.
6. Image-to-Image Translation with Conditional Adversarial Networks - Phillip et al.
7. Cycle-Consistent Adversarial Networks - Jun-Yan et al.
8. StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation - Yunjey Choi et al.
9. Learning from Simulated and Unsupervised Images through Adversarial Training - Shrivastava et al.
10. Are GANs create equal? A Large-Scale Study - Lucic et al.
11. Energy-based Generative Adversarial Network - Zhao et al.
12. Wasserstein GAN - Arjovsky et al.
13. BEGAN: Boundary Equilibrium Generative Adversarial Networks - Berthelot et al.
14. Pixel Recurrent Neural Networks - Oord et al.

Speech Synthesis

1. Tacotron: Towards End-to-End Speech Synthesis - Yuxuan Wang et al.
2. Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions - Jonathan Shen et al.
3. Deep Voice 2: Multi-Speaker Neural Text-to-Speech - Sercan Arik et al.
4. Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning - Wei Ping et al.

Mathmatics

1. A Primer on Optima Transport in NIPS 2017 - Marco Cuturi

Reinforcement Learnings

1. Asynchronous Methods for Deep Reinforcement Learning - Mnih et al.
2. Playing Atari with Deep Reinforcement Learning - Mnih et al.
3. Deep Reinforcement Learning with Double Q-learning

Sequencial Models / NLP

1. Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling - Hasim Sak et al.
2. Sequence to sequence learning with neural networks - Sutskever et al.
3. Very Deep Convolutional Networks for Text Classification - Conneau et al.
4. Deep Learning applied to NLP - Marc Moreno Lopez et al.
5. Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling - Junyoung Chung et al.

Tip / Tutorial Papers

1. Awesome RNN
2. Awesome Public DataSets
3. NIPS tutorial - Generative Adversarial Networks(PDF/Video) - Ian Goodfellow
4. A guide to convolution arithmetic for deep learning - Vincent Dumoulin and Francesco Visin
5. CS 294: Deep Reinforcement Learning
6. David Silver's Reinforcement Learning Course
7. A course on reinforcement learning in the wild

Writing Rules

1. 새로운 논문을 추가할 때는 다른 논문들과 규칙을 맞추어서 작성.
2. 되도록이면 논문의 PDF 파일을 하이퍼링크.
3. Alt Text는 '논문 제목 - 제 1저자' 형식 맞추어 작성.

Repository References

1. Deep Learning Papers Reading Loadmap
2. Awesome Deep Learning Papers