Deep Etc - jungwonkang/references GitHub Wiki

• Understanding LSTM networks (by Colah)
• LSTM (in Korean)
• Illustrated guide to LSTM’s and GRU’s: a step by step explanation
• RNN, LSTM and GRU tutorial
• Generating Sequences With Recurrent Neural Networks
• Conv LSTM
  • Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
  • https://www.quora.com/What-is-the-difference-between-ConvLSTM-and-CNN-LSTM

• Generative Models (Open AI)
• BEGAN: Boundary Equilibrium Generative Adversarial Networks
• All about the GANs
• GAN Lab - Play with GANs in your browser!
• GAN을 이용한 Image to Image Translation: Pix2Pix, CycleGAN, DiscoGAN
• Curated list of awesome GAN applications and demo
• BigGAN
  • BigGAN: A New State of the Art in Image Synthesis
• [VDB(Variational Discriminator Bottleneck)/VAIL(Variation Adversarial Imitation Learning)]
  • Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flow
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Semantic Image Synthesis with Spatially-Adaptive Normalization (Nvidia)

• Reinforcement Learning: a comprehensive introduction [Part 0]
• What is reinforcement learning? The complete guide
• Demystifying Deep Reinforcement Learning

• Graph-neural-networks

• Thomas Kipf (in Max Welling group)

  • https://tkipf.github.io/graph-convolutional-networks/
  • http://tkipf.github.io/misc/SlidesCambridge.pdf (52 pages)
  • http://deeploria.gforge.inria.fr/thomasTalk.pdf (100 pages)

• GNN review (Google deepmind)

• DeepMind's library for building graph networks in Tensorflow and Sonnet

• Graph Attention Networks

• Graph neural networks: variations and applications

• Unsupervised domain adaptation by backpropagation (2015)

  • H-divergence theory: A theory of learning from different domains

• Domain-adversarial training of neural network (2016)

  • Domain-adversarial neural network in tensorflow

• Domain adaptive faster R-CNN for object detection in the wild(CVPR 2018)

• Adversarial discriminative domain adaptation

• Attacking machine learning with adversarial examples

• Adversarial attacks and defences for CNN

Personal

• Sung Kim
• Hwalsuk Lee (in Naver)
  • Character Region Awareness for Text Detection
  • What is wrong with scene text recognition model comparisons? dataset and model analysis
• Taehoon Kim (in OpenAI)
• Yunjey Choi
• Sanja Fidler
• Raquel Urtasun
  • Shenlong Wang
  • Bin Yang

Group

• Uber ATG

• CVPR 2017 tutorial: deep learning for objects and scenes

  • Part 1
  • Part 2

• Unsupervised Pixel-Level Domain Adaptation With Generative Adversarial Networks

• Tutorial on Generative adversarial networks - Domain Adversarial Learning

• Tutorial on Generative adversarial networks - GANs as Learned Loss Functions

• Lesson 12: Deep Learning Part 2 2018 - Generative Adversarial Networks (GANs)

• CS231n: Convolutional Neural Networks for Visual Recognition

  • 2017 Lecture Videos
  • Schedule and Syllabus
  • Course Notes

• VIP AI 101 CheatSheet for All

  • https://montrealartificialintelligence.com/academy/

• Conditional Variational AutoEncoder on the MNIST data set using the PyTroch

• https://www.edureka.co/blog/

• Lunit tech blog (in Korean)

• https://blog.openai.com/

• Variational autoEncoder

• Machine Learning Yearning (in Korean)

• The 50 Best Public Datasets for Machine Learning

• 초짜 대학원생의 입장에서 이해하는 Auto-Encoding Variational Bayes (VAE)

• Deep Learning Drizzle