3185 Introduction to Data Compressing (資料壓縮導論)
-
Course Time: Mon 09:10-12:00
-
Classroom: AT335
-
Course Outlines: 資料壓縮導論--數位通訊逐漸的取代了早先所使用的類比通訊，一個相當高的資料量不論是傳送出去或者儲存起來，都會構成問題，所以資料壓縮是一個用來減少訊號量的程序，從本課程中讓學生能了解且學習到資料壓縮的理論及技術應用範圍。 課程綱要如下:
-
1. Introduction;
-
2. Lossless Compression: Huffman Coding, Arithmetic Coding , Dictionary Techniques, Predictive Coding;
-
3. Lossy Compression: Scalar Quantization, Vector Quantization, Differential Coding;
-
4. Transform Coding, DCT, JPEG, Subband coding, Wavelet-based compression;
-
5. Image Compression Standard;
-
6. Basic Video Coding Techniques;
-
7. Video Compression Standards;
-
8. Basic Audio Compression Techniques;
-
9. MPEG Audio Compression.
-
-
Textbook: "Introduction to Data Compression", by Khalid Sayood, 4th Edition, Academic Press. (Morgan Kaufann Publisher), 2012.
-
Lecture Notes: DC00
-
Grade: 成績 (Updated at 2022/06/20)
-
News:
-
HW1: Problem 2.5 and 2.7
-
HW2: Problem 3.8
-
緊急通知，因資工所有同學確診，周一會進行清消，所以本周(5/16)課程改成線上教學，網址：meet.google.com/bqf-xrxk-juw
-
5/23 課程維持線上上課
-
6/13 線上考試如下，請於當日中午1200前作答完畢，請誠實作答。 https://forms.gle/q9Nx7cRAozQPyuzD7
-
期中考、作業與期末考等成績已公布，有疑問者，請於6/20上午0900-1200找助教，逾時不後。
-
學期成績已公布，有疑問者，請於6/22下午1500-1600與我聯絡，逾時不後。
-
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, RandomVectors, PR2a, PR2b, PR06
-
Grade: 成績 (Updated at 2022/06/20)
-
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: Unsupervised clustering using Kohonen Network for the dataset in HW1.
-
因上課同學有人確診，所以本周(5/17)課程改成線上教學，網址：meet.google.com/yea-qxth-qcs
-
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5/31交，題目內容須用到本課程所涵蓋的分類器(classifiers)，含深度學習。6/7, 14 期末分組報告。
-
5/31 舉行期末考試。
-
5/24 課程維持線上上課
-
5/31 線上考試如下，請於當日下午1600前作答完畢，請誠實作答。
https://forms.gle/AEVWfwXZUoFW1RNx5 -
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：140.120.182.2, Port：1023, 帳號：PR_Student_2022, 密碼：2022PRClass
-
作業成績與期中考成績已公布。
-
期中考、作業與期末考等成績已公布，有疑問者，請於6/20上午0900-1200找助教，逾時不後。
-
期末報告、學期成績已公布，有疑問者，請於6/22下午1500-1600與我聯絡，逾時不後。
-
1923 Introduction to Deep Learning in Image Processing (深度學習概論與影像處理應用)
-
Course Time: August 29th, 30th, and 31th 09:10-16:00
-
Classroom: S821 (Room 821@Science Building)
-
Course Outlines:
-
1. Introduction to Machine Learning
-
2. Multilayer Perceptron
-
3.Deep Convolutional Neural Networks
-
4.Object Detection and Classification
-
5.Deep learning on the Raspberry Pi.
-
-
Reference Books:
-
[1] "Artificial Inteligence" by Leonardo Araujo dos Santos. 2018.
-
[2] "Hands-On Computer Vision with TensorFlow 2", by Benjamin Planche and Eliot Andres, Packt Publishing, 2019.
-
[3] “Neural Networks and Learning Machines” by Simon O. Haykin, 3rd Edition, 2009
-
-
Grade:
-
News:
