CE6143 - Introduction to Data Science (Fall 2021)

Lecture language: English

Final project presentation slides

Group	Title	Slides
1	PM2.5 Prediction Based on Transformer	PDF
2	Text Localization and Recognition on Complex Street View	PPTX
3	How to Recognize Fake Accounts on Instagram?	PPTX
4	Auto Regression Forecast Model for Electricity Production	PPTX
5	(Dropped)
6	Shuttlecocks Checker -- a Case Study on Classification Using CNN Model	PPTX
7	Image Colorization and De-noising	PPTX
8	Compare Various Classification Algorithms Using MNIST	PPTX
9	Pothole Detection	PPTX
10	AI in Medical Imaging	PPTX
11	Stock Prediction System	PPTX
12	Recognizing the Printed and Handwritten Numbers on the Steel Billet	PPTX
13	Automatic Detection of Firearm in Surveillance Camera	PPTX
14	Genre Classification of IMDb	PPTX
15	Gesture Recognition Using mmWave Sensors	PPTX
16	(Dropped)
17	Wine Quality DataSet -- Predict Wine Quality	PDF
18	Continuous Sign Language Recognition	PPTX

Announcement

[IMPORTANT] If you need a passcode, please attend the online course of the first week using this URL

Meeting time

14:00 - 16:50 Tuesday

Location

~~A306, Engineering Building 5~~ Live stream

Recommended textbooks

"The Elements of Statistical Learning" by Trevor Hastie, Robert Tibshirani, and Jerome Friedman
download
"Deep Learning" by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
download

Staff

Instructor: Hung-Hsuan Chen (陳弘軒)
Office hour: after class or by appointment.
TA: Tong-Yi Kuo (郭同益), Yuan-Chih Yang (楊緣智)
Office hour: by appointment

Grading

Exercise: 55%
Project proposal and progress presentation: 10%
Project final presentation and report: 30%
Others: 5%

Slides

Please download from new ee-class

Progress (subject to change)

Week	Date	Content	Exercise
1	9/14	1. Overview of the course
2	9/21	Holiday
3	9/28	1. Introduction to ML 2. KNN 3. k-means	Exercise 1 (due: 10/4 23:59:59)
4	10/5	1. Distance measures 2. Entropy 3. Decision tree
5	10/12	1. Decision tree 2. Matrix derivatives	Exercise 2 (due: 10/25 23:59:59)
6	10/19	Linear regression and regularization (Lasso, Ridge, Elastic-net) TA session: Introduction to Python and popular scientific libraries in Python
7	10/26	1. Logistic regression and gradient ascent 2. Precision, recall, ROC curve, PR cure, and other measures
8	11/2	1. Evaluation metrics for classification 2. SVM	Exercise 3 (due: 11/22 23:59:59)
9	11/9	Midterm project proposal presentation
10	11/16	1. Regularized linear regression and classification 2. Linear SVM with poly-2 terms vs Polynomial Kernel SVM
11	11/23	1. Practical considerations 2. Recommender systems
12	11/30	1. Recommender systems 2. Differentiating regularization weight 3. Factorization Machine and Field-aware Factorization Machine 4. Learning to rank
13	12/7	1. Learning to rank 2. Deep neural network	Exercise 4 (due: 12/20 23:59:59)
14	12/14	Convolutional neural network
15	12/21	1. Associated Learning 2. Recurrent neural network
16	12/28	1. Attention model 2. Word embedding and graph embedding
17	1/4	Final project presentation
18	1/12	Final wrap-up	Final project report (due: 1/11 23:59:59)