6638 Pattern Recognition
-
Course Time: Tue 13:10-16:00
-
Classroom: AT338
-
Course Outlines:
-
1.Introduction;
-
2.Bayes Decision Theory;
-
3.Maximum-Likelihood and Bayesian Parameter Estimation;
-
4.Nonparametric Techniques;
-
5.Multilayer Neural Networks;
-
6. Deep Learning - Convolutional Neural Networks;
-
7. Unsupervised Learning and Clustering.
-
8. Feature Extraction - Linear Discriminant Analysis and Principle Component Analysis;
-
9. Deep Learning - Autoencoder;
-
-
Textbook: "Pattern Classification", by Richard O. Duda, Peter E. Hart and David G. Stork, John Wiley & Sons, 2nd edition, 2001.
-
Reference Books:
-
Introduction to Statistical Pattern Recognition, by Keinosuke Fukunaga, 2nd Edition, Academic Press, 1990.
-
Neural Networks and Learning Machines, 3rd Edition, Simon O. Haykin, McMaster University, Ontario Canada, Pearson, 2009.
-
"Artificial Intelilgence" by Leonardo Araujo dos Santos. 2018.
-
"Deep Learning", by Ian Goodfellow, Yoshua Bengio, and Aaron Courville, MIT Press, 2016.
-
-
Grade: PR成績 (Updated at 2023/06/19)
-
News:
-
HW1: Design the Maximum A Posterior (MAP) classifier for the UCI-WINE dataset (3 classes, 13 features). Half of the data are used in the training phase, and the rest is for evaluation. You can download the WINE dataset from [WINE_UCI]. The deadline is 2nd May.
-
HW2: Compute the upper bound of Bayes error (Chernoff bound) for the UCI-WINE dataset. The deadline is 9th May.
-
作業繳交方式：內容為主要演算法與程式片斷，包含測試資料與結果，以及簡短的討論或結論等。請把書面報告電子檔，程式及相關測試資料先以Winzip或WinRAR壓縮，並以學號為其檔名，上傳到指定的FTP網站：主機IP:140.120.182.181，使用者名稱:PR_Student_111，密碼:prstudent
，port:21。 -
HW3: Implement the Kohonen Self-Organizing Feature Map network for the unsupervised clustering of the UCI-WINE dataset. The deadline is 23th May.
-
期末報告每組2-3人，報告論文須為近3年的論文，分組名單與論文題目摘要請於5/23交，題目內容須用到本課程所涵蓋的分類器(classifiers)，含深度學習。
-
5/23 期末考筆試。
-
5/30，6/6，6/13期末分組報告。
-
作業、期末報告、期末考與等學期成績已公布，有期末考疑問者，請於6/20下午1300-1600找助教，學期成績有疑問者，請於6/20下午1300-1600與我聯絡，逾時不後。
-
-
深度學習概論與電腦視覺應用
-
code: mlp