기계학습(Machine Learning)

0. AlphaGo의 인공지능 알고리즘 분석 보고서 (출처: SPRi) [PDF]
1. Introduction [PDF]
2. Supervised Learning [PDF]
3. Bayesian Decision theory [PDF]
4-1. Parametric Methods - 1 [PDF]
4-2. Parametric Methods - 2 [PDF]
5. Multivariate Methods [PDF]
6-1. Dimensionality Reduction - 1 [PDF]
6-2. Dimensionality Reduction - 2 [PDF]
6-3. Dimensionality Reduction - 3 [PDF] (wiki: Nonlinear dimensionality reduction) (t-SNE demo)
7. Clustering [PDF]
8. Nonparametric Methods [PDF]
9. Decision Trees [PDF]
10. Linear Discrimination [PDF]
11. Multilayer Perceptrons [PDF]
11-2. Deep Learning - Introduction [PDF]
11-3. Convolutional Neural Network (taken from http://www.cse.ust.hk/~leichen/courses/FYTG-5101) [PDF]
11-4. Convolutional Neural Network - 2 (taken from http://web.engr.illinois.edu/~slazebni/spring14) [PDF]
11-5. CNN - Deep Residual Learning (taken from http://kaiminghe.com/ilsvrc15/ilsvrc2015_deep_residual_learning_kaiminghe.pdf) [PDF] (ConvNetJS)
11-6. RNN and NLP application [PDF]
11-7. Mini-batch gradient descent, momentum method, adaptive learning rate, and rmsprop (taken from http://www.cs.toronto.edu/~tijmen/csc321/) [PDF] [PDF-2] (SGD, momentum, and RMSprop - 1) (SGD, momentum, and RMSprop - 2)
11-8. Batch Normalization (taken from https://bcourses.berkeley.edu/ CS294) [PDF]
11-9. Generative Adversarial Networks [PDF] [example] [video-1]
12. Local Models
13. Kernel Machines
14. Bayesian Estimation
15. Hidden Markov Models
16. Graphical Models
17. Combining Multiple Learners
18. Reinforcement Learning [PDF]
19. Design and Analysis of Machine Learning Experiments