Deep Learning Tutorials
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
lecture_notes
papers
.DS_Store
.gitignore
README.md

README.md

#Deep Learning Tutorials These tutorials are for deep learning beginners which have been used in a six week Deep Learning and Computer Vision course. Hope these to be helpful for understanding what deep learning is and how it can be applied to various fields including computer vision, robotics, natural language processings, and so forth.

##Week1

  1. Introduction to the Class
  2. Introduction to Deep Learning (LeCun's slide)
  3. Introduction to Deep Learning Tools (Karpathy's slide)
  4. Introduction to TensorFlow

###Week2

  1. What is the algorithm behind AlphaGo?
  2. GoogLeNet
  3. Optimization methods (momentum, adagrad, adadelta, rmsprop, adam)
  4. Restricted Boltzmann Machine
  5. Denoising Auto Encoder

###Week3

  1. Semantic segmentation (fully convoluional net, deconvolutional net)
  2. Weakly supervised localization (class-activation map with global average pooling)

###Week4

  1. Recurrent Neural Network (+Long Short Term Memory)
  2. Word Embedding (Word2Vec)
  3. Image Caption Generation

###Week5

  1. Deep Q Learning
  2. Word Embedding (Word2Vec)
  3. Image Detection (R-CNN, Spatial Pyramid Pooling Net, Fast R-CNN, Faster R-CNN, and YOLO)
  4. Visual QnA (Hyunwoo's)

###Week6

  1. Super Resolution (Jiwon's)
  2. Residual Learning (ResNet)
  3. VGG Net
  4. Fine-tuning with VGG Net
  5. Neural Style (texture synthesis + reconstruction)
  6. Adversarial Attack
  7. Generative Adversarial Network