章節

• 第一週：監督式學習與機器學習
  • ● 1-1. Supervised learning
  • ● 1-2. Decision trees - example
  • ● 1-3. Decision trees - how to choose attribute
  • ● 1-4. Decision trees- overfitting / ending
  • ● 1-5. Evaluating and Choosing the best hypothesis - intro / k-fold
  • ● 第一週練習題
• 第二週：參數模型
  • ● 2-1. Evaluating and Choosing the best hypothesis-peeking - error rate / regularization
  • ● 2-2. Regression and classification with linear models - Univariate linear regression part1
  • ● 2-3. Regression and classification with linear models - Univariate linear regression part2
  • ● 2-4. Decision trees - overfitting / ending
  • ● 2-5. Regression and classification with linear models - multivariate linear regression
  • ● 第二週練習題
• 第三週：非參數模型
  • ● 3-1. Regression and classification with linear models - Linear classifiers with a hard threshold
  • ● 3-2. Regression and classification with linear models - Linear classification with logistic regression
  • ● 3-3. Nonparametric models - nearest neighbor models part1
  • ● 3-4. Nonparametric models - nearest neighbor models part2
  • ● 3-5. Nonparametric models-nearest neighbors/locality sensitive hashing
  • ● 第三週練習題
• 第四週：SVM 與集成學習
  • ● 4-1. Nonparametric models - regression
  • ● 4-2. SVM - part1 intro
  • ● 4-3. SVM - part2 how to find margin
  • ● 4-4. SVM - part3 nonlinear space
  • ● 4-5. Ensemble - bagging
  • ● 第四週練習題
• 第五週：集成學習的種類
  • ● 5-1. Ensemble - random Forest / stacking
  • ● 5-2. Ensemble - boosting
  • ● 5-3. Ensemble - online learning
  • ● 5-4. Developing machine learning systems
  • ● 第五週練習題
• 第六週：深度學習與CNN
  • ● 6-1. Deep learning intro
  • ● 6-2. Gradient and learning
  • ● 6-3. Computing graph / hidden layers
  • ● 6-4. CNN part 1
  • ● 6-5. CNN part 2
  • ● 第六週練習題
• 第七週：梯度計算
  • ● 7-1. Pooling / CNN tensor
  • ● 7-2. Residual network / Learning algorithm
  • ● 7-3. Compute grad in computing graph / Batch normalization
  • ● 7-4. Generalization - choose a net structure / architecture search
  • ● 7-5. Generalization - weight decay / drop out
  • ● 第七週練習題
• 第八週：RNN和非監督式學習
  • ● 8-1. RNN
  • ● 8-2. Unsupervised learning intro / PCA
  • ● 8-3. Unsupervised learning - auto encoder
  • ● 8-4. Unsupervised learning - auto regressive / GAN / translation
  • ● 8-5. Transfer learning and multitask learning / application
  • ● 第八週練習題
• 第九週：強化式學習
  • ● 9-1. Reinforcement learning intro
  • ● 9-2. Passive reinforcement learning part 1
  • ● 9-3. Passive reinforcement learning part 2
  • ● 9-4. Direct utility estimation
  • ● 第九週練習題
• 第十週：主動式強化學習
  • ● 10-1. Adaptive dynamic programming / Temporal-difference learning part 1
  • ● 10-2. Temporal-difference learning part 2
  • ● 10-3. Active reinforcement learning part 1
  • ● 10-4. Active reinforcement learning part 2
  • ● 第十週練習題
• 第十一週：深度學習中的強化式學習
  • ● 11-1. Temporal-difference Q-learning
  • ● 11-2. Generalization in reinforcement learning
  • ● 11-3. Deep reinforcement learning
  • ● 第十一週練習題

講師

朱威達

多媒體系統、機器學習、電腦視覺 ｜ 查看講師

評價