校際選修

115-1 選課時程

進行中

  • 初選第一階段 6/15/2026
  • 初選第二階段 6/22/2026
  • 校際選修 8/24/2026
  • 初選第三階段 8/31/2026
  • 開學後加退選 9/7/2026
  • 逾期加退選 9/21/2026
選課資源

圖形識別概論

Introduction to Pattern Recognition

學期
114-2
學分
3 學分
當期課號
515617
永久課號
CSCS20010
開課單位
資訊工程學系
授課教師
林彥宇
校區
光復
類別
選修
上課時間表
週三
3
10:10–11:00
圖形識別概論
ED102
3 節連堂
4
11:10–12:00
N
12:20–13:10

* 根據陽明交大上課時間表所列

概述

I will introduce several representative algorithms for pattern recognition and generation, including linear models, neural networks, ensemble methods, kernel methods, convolutional neural networks, transformers, mamba, and generative models.

先修科目

Linear algebra, probability, calculus, programming (such as Python), and deep learning programming (such as PyTorch, Keras, or TensorFlow)

評分方式

Four Homework Assignments: 30% (= 7.5% x 4) Midterm Exam: 35% Final Exam: 35%

週次計畫
週次主題
第 1 週Introduction
第 2 週Linear Model for Regression
第 3 週Linear Model for Classification
第 4 週Neural Networks
第 5 週Ensemble Model I
第 6 週Ensemble Model II
第 7 週Kernel Method I
第 8 週Midterm Exam
第 9 週Kernel Method II
第 10 週Deep Neural Networks (DNN)
第 11 週Convolutional Neural Networks (CNN) I
第 12 週Convolutional Neural Networks (CNN) II and Transformers I
第 13 週Transformers II
第 14 週Mamba
第 15 週Final Exam
第 16 週Diffusion Models
教科書

1. C. Bishop, Pattern Recognition and Machine Learning, Springer 2006 https://www.springer.com/gp/book/9780387310732 Free pdf download: https://www.microsoft.com/en-us/research/uploads/prod/2006/01/Bishop-Pattern-Recognition-and-Machine-Learning-2006.pdf 2. Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press, 2016 Free pdf download: https://www.deeplearningbook.org/

Office Hours
地點
EC234-C (TA), EC701 (TA), or EC706 (Instructor) Please send us an email in advance to make an appointment, and we will inform you where to have a discussion.
時間
Wednesday 1:00 pm ~ 2:00 pm
聯絡方式
Instructor: Yen-Yu Lin (林彥宇) Email: lin@cs.nycu.edu.tw TAs: Wei-Hsiang Yu (游為翔) Email: weihsiang.yu@gmail.com Yu-Chi Chung (鍾育騏) Email: cs0905555581@gmail.com Yu-Hsuan Tang (湯于萱) Email: yuijw0720@gmail.com