Machine Learning 2019 Spring

Syllabus

Date Review Topic New Topic Homework
2/21 Regression, Gradient Descent (link,link,link,link,link,link) Overview(pdf,ppt,video), Rule(pdf,ppt) HW1: regression (link)
2/28 Where does the error come from, Classification, Logistic Regression (link,link,link)
3/07 Deep Learning, Backpropagation (link,link) Anomaly Detection (pdf,ppt,video) HW2: classification (link)
3/14 CNN (link), keras (link,link,link) Adversarial Attack (pdf,ppt,video)
3/21 Training Deep Models (link,link,link) Explainable ML(pdf,ppt,video) HW3, 4: CNN, Explainable AI (link,link)
3/28 RNN (link,link) Ordered (莊永松) link HW5: Attack (link)
4/04 Ensemble (link)
4/11 Semi(link), Transfer(link) Life-long learning (pdf,ppt,video)
4/18
4/25 Seq2seq (link) Meta Learning (pdf,ppt,video) HW6: RNN (link)
5/02Unsupervised Learning (link,link,link) Meta Learning (pdf,ppt,video,video) 機器學習實戰演練
5/09 Unsupervised Learning (link,link,link) More Auto-encoder (pdf,ppt,video) HW7: unsupervised (link)
5/16 Reinforcement Learning (link,link,link,link(optional)) More Semi (陳奕禎), More Attack (徐瑞陽)
5/23 Network Compression (pdf,ppt,video) HW8: Network Compression
5/30 GAN (link) Transformer(pdf,ppt,video)
6/06 BERT (pdf,ppt,video)