top of page

2021APR.JPG

3185 Signals and Systems

  • Course Time: Mon 09:10-12:00

  • Classroom: AT335

  • Course Outlines: This course covers fundamental concepts in signals and systems, which are broadly used for modeling, analyzing, and designing physical processes. Both the continuous-time and the discrete-time aspects will be considered. This course can be viewed as the prerequisite for the advanced courses such as linear systems, communication systems and digital signal processing.  The course is outlined as:

    • 1. Introduction to signals and systems;

    • 2. Linear time-invariant systems;

    • 3. Fourier series representation for periodical signals;

    • 4. Fourier analysis for continuous-time signals and systems;

    • 5. Fourier analysis for discrete-time signals and systems;

    • 6. Sampling;

    • 7. Filtering;

    • 8. Laplace transform and Z-transform. 

  • Textbook: "Signals and Systems", by A. Oppenheim, A. Willsky, and H. Nawab, 2nd Edition, Prentice Hall, 1997.

  • Lecture Notes:  Chapter0, SS03

  • Grade:  成績(Updated at 2021/06/19)

  • News:

    • HW1: 1.9,  1.19, 1.25, 1.27

    • HW2: 2.8 and 2.14

    • 本周因為疫情爆發,事出突然,課程改為自主學習,我已把第三章傅立葉級數的投影片放到網站,請大家先研讀。然後請把Google Meet準備好,下周暫定會用Google Meet線上上課。相關事宜,請隨時注意此教學網站的公告,謝謝! 

    • 5/24早上的課使用Google Meet線上上課,會點名,網址為:https://meet.google.com/cjj-arpj-wcy

    • ​期中考與作業等成績已經公佈,有疑問找請於6/18與我聯絡。

    • 學期成績已經公佈,有疑問找請於6/23前與我聯絡,逾時不後,成績將送教務處。

 

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.

  • Lecture Notes:  PR00, PR10, FeatureExtration

  • Grade:   成績 (Updated at 2021/06/23)

  • News: 

    • HW1: Generate the Gaussian high dimensional dataset. (Stationary random process).

  • HW2: Design the Maximum A Posterior  (MAP) classifier for the dataset in HW1.  Half of the data are used in the training phase, and the rest is for evaluation.

  • HW3: Compute the upper bound of Bayes error (Bhattacharyya bound) or the dataset in HW1.

  • HW4: Design the Multi-Layer Perceptron (MLP) classifier for the dataset in HW1.  Half of the data are used in the training phase, and the rest is for evaluation.

  • 本周因為疫情爆發,事出突然,課程改為自主學習,我會把unsupervised learning投影片放到網站,密碼為PR21,請大家先研讀。請大家這兩周趕快把作業都完成。然後請把Google Meet準備好,下周可能會用Google Meet線上上課或測驗。相關事宜,請隨時注意此教學網站的公告,謝謝! 

  • 5/25起的課使用Google Meet線上上課,會點名,網址為:https://meet.google.com/eaq-cfbs-gau

  • 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,上傳到下列的FTP網站:IP:140.120.182.172,PORT: 1023,使用者名稱: prstudent,密碼: pr2021

  • Final Project: 期末報告每組3-4人,報告論文須為近3年的SCI論文,分組名單與論文題目摘要請於6/1交,題目內容須用到本課程所涵蓋的分類器(classifiers),含深度學習。

  • 6/8, 15 期末分組報告

  • ​期末報告與作業等成績已經公佈,有疑問找請於6/18與我聯絡。

  • 學期成績已經公佈,有疑問找請於6/23前與我聯絡,逾時不後,成績將送教務處。

7748 Image Analysis and Recognition (影像分析與辨識)

  • Course Time: Wed 18:20-21:00

  • Classroom: S113 

  • Course Outlines: This course covers fundamental concepts and methods in image analysis and recognition. The course is outlined as:

    • 1. Introduction

    • 2. Digital Image Fundamentals

    • 3. Intensity Transformations and Spatial Filtering

    • 4. Morphological Image Processing

    • 5. Image Segmentation

    • 6. Deep Learning - Convolutional Neural Networks

    • 7. Image Classification and Object Detection with Convolutional Neural Networks.

    • 8. Deep Learning - Autoencoder

    • 9. Deep Learning - Generative Adversarial Network

  • Textbook: "Digital Image Processing", by R. C. Gonzalez and R. E. Woods, 4th Edition, Pearson (開發), 2017.

  • Reference Books:  "

    • Digital Image Processing Using MATLAB", 2nd Edition, by Rafael C. Gonzalez, Richard E. Woods, Steven L. Eddins, 
      McGraw-Hill, 2009.

    • "Artificial Inteligence" by Leonardo Araujo dos Santos. 2018.

    •  "Hands-On Computer Vision with TensorFlow 2", by Benjamin Planche and Eliot Andres, Packt Publishing, 2019.

  • Lecture Notes: IAR00, 關於PPT授課著作權DIP12

  • Grade:  成績 (Updated at 2021/06/19)

  • News:

    • HW1: Image Perspective crop using affine transform and  bilinear interpolation.

    • 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,網址等資訊隨後公布。

    • HW2: Image enhancement by using convolution with Sobel filer, Laplacian filter, and Averaging filter.

    • HW3: Graylevel morphology:  Morphological Smoothing ,Morphological Gradient and Top-hat Transformation.

    • 本周因為疫情爆發,事出突然,課程改為自主學習,我會把image classification投影片放到此網站,密碼為IAR21,請大家先研讀。請大家這兩周趕快把作業都完成然後請把Google Meet準備好,下周可能會用Google Meet線上上課或測驗。相關事宜,請隨時注意此教學網站的公告,謝謝! 

    • 5/25晚上起的課使用Google Meet線上上課,會點名,網址為:https://meet.google.com/qev-mznp-bfq

    • Final Project: 期末報告每人一組,報告論文須為近3年的SCI論文,分組名單與論文題目摘要請於6/2交,題目內容須與影像分析或深度學習相關。

    • 6/9, 16 期末分組報告

    • 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,上傳到下列的FTP網站:主機: 140.120.182.172,PORT: 1023,使用者名稱: iarstudent,密碼: iar2021

    • ​期末報告與作業等成績已經公佈,有疑問找請於6/18與我聯絡。

    • 學期成績已經公佈,有疑問找請於6/23前與我聯絡,逾時不後,成績將送教務處。

1505 Business Computer Programming (商業程式設計)

  • Course Time: Tue 18:20-20:00

  • Course Outlines: 學習R語言於統計與資料分析的應用,R語言程式設計,R語言繪圖與報表,與R語言在人工智慧等的應用。內容包含有:

    • 1. RStudio 開發環境的建置與介紹; 

    • 2. 變數型態、向量運算、函數的使用; 

    • 3. 各種資料的讀取與匯入; 

    • 4. 直覺、吸睛的繪圖技巧; 

    • 5. 原始資料的整併和取樣; 

    • 6. 字串的處理與運算; 

    • 7. 迴圈、向量等群組資料的操作; 

    • 8. 報表、簡報和網頁呈現的技巧; 

    • 9. 各種統計、迴歸資料模型的應用; 

    • 10. R語言實作於深度學習CNN

  • Textbook: R 軟體 資料分析基礎與應用 第二版 2019  (R for Everyone: Advanced Analytics and Graphics),旗標出版公司

  • Reference Book:  R in Action: Data Analysis and Graphics With R, by Kabacoff, Robert I., Manning Pubns Co., 2015 

  • Lecture Notes: R2021

  • Grade: 成績(Updated at 2021/06/22)

  • ​News:
    • HW1: 請寫一個程式模擬骰子丟100次的結果,計算平均值並畫出骰子結果統計圖。​

    • 4/13 小考。 

    • HW2: 使用while迴圈計算1-1000的7的倍數和。

    • HW3: 請找出兩位數中,其十位數與個位數和為10的所有整數。

    • HW4: 畫XY散佈圖-使用plot函式。資料的X與Y均為uniform distribution,數字範圍為0-10,產生100個點並畫出。

    • 本周因為疫情爆發,事出突然,課程改為自主學習,請大家好好把迴圈與條件判斷式練習好,也請大家這兩周趕快把作業都完成然後請把Google Meet準備好,下周可能會用Google Meet線上上課或測驗。相關事宜,請隨時注意此教學網站的公告,謝謝! 

    • 5/25起的課使用Google Meet線上上課,會點名,網址為:https://meet.google.com/djm-indp-fwq

    • HW5: 使用R語言求解以下國一數學題目:考慮滿足下列兩個條件的二位數:(1)個位數字的2倍減去十位數字的差大於2; (2)十位數字的3倍與個位數字的和小於23,則滿足條件最大的二位數為多少? (重要作業,分數加倍計算)

    • HW6: 使用R語言求解以下國一數學題目:有一最簡分數,其分子、分母和為70,將其化為小數並四捨五入後為0.6,則此分數為何? (重要作業,分數加倍計算)

    • ​期中考與作業等成績已經公佈,有疑問找請於6/18與我聯絡。

    • 學期成績已經公佈,有疑問找請於6/23前與我聯絡,逾時不後,成績將送教務處。

Machine Learning (資訊科技第二專長學分班)

  • Course Time: Mon 18:20-21:00

  • Classroom: AT337

  • Course Outlines: 

    • 1.Introduction to Machine Learning;

    • 2. K-Nearest Neighbors;

    • 3. Naive Bayesian Classification;

    • 4. Decision Trees and Random Forests;

    • 5. Support Vector Machines;

    • 6.  Neural Networks;

    • 7. Unsupervised Learning and Clustering;

    • 8. Deep Learning

  • Textbook: “初探機器學習 使用Python”, O’Reilly, 2017(碁峰) (Thoughtful Machine Learning with Python: A Test-Driven Approach 1st Edition -Matthew Kirk)

  • Reference Books:  

    • “Introduction to Statistical Pattern Recognition” by Keinosuke Fukunaga, Academic Press, 2nd edition,1990.

    • “Neural Networks and Learning Machines” by Simon O. Haykin, Pearson Education, Inc., 3rd Edition, 2009.

    • “Artificial Intelligence” - Leonardo Araujo dos Santos. 2018.

  • Lecture Notes:  ML00, MLP

  • Grade:  成績(Updated at 2021/06/23)

  • News: 

    • HW1:  Design the Maximum A Posterior  (MAP) classifier for the WINE dataset using 1 feature. Half of the data are used as the training set, and the other half is used for validation. 

    • HW2:  Design the Maximum A Posterior  (MAP) classifier for the WINE dataset using ALL features. Half of the data are used as the training set, and the other half is used for validation. 

    • 本周因為疫情爆發,事出突然,課程改為自主學習,我已把多層感知機(MLP)的投影片放到此網站,密碼:ML21,請大家先研讀。然後請把Google Meet準備好,下周暫定會用Google Meet線上上課。相關事宜,請隨時注意我的教學網站的公告,謝謝! 

    • 5/24晚上的課使用Google Meet線上上課,會點名,網址為:https://meet.google.com/dxr-hojq-kis

    • ​期中考與作業等成績已經公佈,有疑問找請於6/18與我聯絡。

    • 學期成績已經公佈,有疑問找請於6/23前與我聯絡,逾時不後。

PReq1.png
bottom of page