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

Deep Learning

學期
109-2
學分
3 學分
當期課號
5092
永久課號
ECM9042
開課單位
電信工程研究所
授課教師
簡仁宗
校區
光復
類別
選修
上課時間表
週五
5
13:20–14:10
深度學習
ED219
3 節連堂
6
14:20–15:10
7
15:30–16:20

* 根據陽明交大上課時間表所列

概述

Deep learning is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data by using a deep graph with multiple processing layers, composed of multiple linear and nonlinear transformations. Various deep learning architectures such as deep neural networks, convolutional deep neural networks, deep belief networks and recurrent neural networks have been applied to the fields like computer vision, automatic speech recognition, natural language processing, data mining and bioinformatics. State-of-the-art results on various tasks have been successfully developed.

先修科目

Calculus, Linear Algebra, Probability & Statistics

教學方式

Teaching notes or slides will be provided. Teacher assistants (朱長亭、張哲瑋、田修瑋、黃毓涵、張譽瀚、賴偉偉) will be available at PM19:00-20:00 in week days. Appointments are required. Due to the pandemic of COVID-19, you are encouraged to use online discussion function in E3. TAs will promptly reply your questions.

評分方式

Temporary Policy: Final Exam or Task Competition (25%), Homework (40%), Final Project (35%), Class Attendance (+10%)

課程大綱
週次計畫
週次主題
第 1 週Introduction to Deep Learning
第 2 週Deep Feedforward Networks
第 3 週Regularization for Deep Learning/Tutorial for Pytorch and GPU Server
第 4 週Convolutional Neural Networks
第 5 週Optimization for Deep Models
第 6 週National Holiday
第 7 週Optimization for Deep Models
第 8 週Recurrent Neural Networks and Memory Networks
第 9 週Attention Mechanism and Transformer
第 10 週Auto-Encoders and Approximate Inference
第 11 週Variational Auto-Encoders
第 12 週Generative Adversarial Networks
第 13 週Stochastic Modeling & Reinforcement Learning
第 14 週Reinforcement Learning
第 15 週Self Supervised Learning
第 16 週Project Presentation (ED219)
第 17 週Project Presentation (ED219)
第 18 週Task competition (June 20-25)
教科書

1. I. Goodfellow and Y. Bengio and A. Courville, Deep Learning, The MIT Press, 2016 (http://www.deeplearningbook.org) 2. S. Watanabe and J.-T. Chien, Bayesian Speech and Language Processing, Cambridge University Press, 2015. 3. J.-T. Chien, Source Separation and Machine Learning, Academic Press, 2018. 4. M.-W. Mak and J.-T. Chien, Machine Learning for Speaker Recognition, Cambridge University Press, 2020.

Office Hours
地點
ED 912
時間
PM18:00-18:30 on Monday. Appointments are required.
聯絡方式
jtchien@nctu.edu.tw