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

深度學習與實務

Deep Learning and Practice

學期
110-2
學分
3 學分
當期課號
5254
永久課號
IOC5184
開課單位
資訊科學與工程研究所
授課教師
彭文孝、吳毅成、陳永昇
校區
光復
類別
選修
上課時間表
週二
週四
N
12:20–13:10
深度學習與實務
EC114
3 節連堂
5
13:20–14:10
6
14:20–15:10
A
18:30–19:20
深度學習與實務
EC114
3 節連堂
B
19:30–20:20
C
20:30–21:20

* 根據陽明交大上課時間表所列

概述

(1) To understand the maths of deep learning techniques (2) To familiarize with deep learning tools, such as PyTorch, Tensor Flow, etc. (3) To understand the latest developments and applications of deep learning techniques (4) To develop practical working systems

先修科目

Linear Algebra, Probability Theory, Machine Learning (suggested) NOTE: (1) To submit final projects as academic papers (2) To hold exhibition to showcase final projects (3) To encourage students to participate in various challenges in the fields of computer vision, gaming, data analytics, etc.

評分方式

Labs (done individually) 40%, Paper presentention (done in groups of 3 members) 20% Final project (done in groups of 3 members) 20% Final exam 20%

週次計畫
週次主題
第 1 週1. Introduction 2. Introduction to Reinforcement Learning 3. Reinforcement Learning for Lightweight Model
第 2 週1. Machine Learning Basics - Linear Algebra - Probability and Information Theory - Numerical Computation 2. Warm-up (Python + PyTorch)
第 3 週1. Deep Networks - Deep Feedforward Networks - Convolutional Networks 2. Valued Based Reinforcement Learning
第 4 週1. Convolutional Networks 2. Back-Propagation (Lab 1)
第 5 週1. Recurrent and Recursive Nets 2. Regularization for Deep Learning 3. 2048 TD (Lab 2)
第 6 週1. Deep Learning Research - Linear Factor Models - Autoencoders 2. Convolutional Nets (Lab 3)
第 7 週1. Autoencoders 2. Generative Adversarial Networks 3. No class(4/5)
第 8 週1. Generative Adversarial Networks 2. Convolutional Nets (Lab 4)
第 9 週1. Structured Probabilistic Models for Deep Learning 2. Recurrent Nets and Variational autoencoders (Lab 5)
第 10 週1. Monte Carlo Method 2. Approximate Inference 3. Policy-based Reinforcement Learning
第 11 週1. Normalizing Flows 2. Graph Convolutional Neural Networks 3. Deep Reinforcement Learning (Lab 6)
第 12 週Paper & project proposal presentation
第 13 週1. Paper & project proposal presentation 2. Generative adversarial networks (Lab 7)
第 14 週Paper presentation
第 15 週Paper presentation
第 16 週Paper presentation
第 17 週Final Exam
第 18 週TBD
教科書

1. I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, 1st Ed., MIT Press, Dec. 2016 2. R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, Nov. 2017