深度學習與實務
Deep Learning and Practice
| 節 | 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
(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
Linear Algebra, Probability Theory, Machine Learning (suggested) 4XEF-EC114 (for lectures) 2IJK-EC114 (for Lab) NOTE: (1) The first lecture will begin on Mar. 3 (2IJK-EC114). (2) If you want to enroll in this course, you need to be present on Mar. 3 (2IJK-EC114) and submit your enrollment form in person (if you have not yet been enrolled successfully). (3) Be advised that if we have more students taking this course than we could afford, your final enrollment will be subject to review by all the instructors. (4) More details will be announced during the first lecture. Make sure that you don't miss it.
Labs (done individually) 40%, Paper presentention (done in groups of 2 members) 20% Final project (done in groups of 2 members) 20% Final exam 20%
| 週次 | 主題 |
|---|---|
| 第 1 週 | 1. Introduction 2. Machine Learning Basics - Linear Algebra - Probability and Information Theory - Numerical Computation |
| 第 2 週 | 1. Introduction to Reinforcement Learning 2. Deep Neural Networks - Deep Feedforward Networks - Convolutional Networks |
| 第 3 週 | 1. [Lab] Warm-up (Python + PyTorch) 2. Deep Neural Networks - Convolutional Networks |
| 第 4 週 | 1. [Lab] Back-Propagation 2. Deep Neural Networks - Optimization Deep Models for Training - Recurrent and Recursive Nets |
| 第 5 週 | 1. [Lab] Convolutional Nets |
| 第 6 週 | 1. [Lab] Convolutional Nets 2. Deep Neural Networks - Regularization for Deep Learning |
| 第 7 週 | 1. [Lab] Recurrent Nets 2. Deep Learning Research - Linear Factor Models - Autoencoders |
| 第 8 週 | 1. Reinforcement Learning for Lightweight Model 2. Deep Learning Research - Autoencoders - Generative Adversarial Networks |
| 第 9 週 | 1. [Lab] Variational autoencoders 2. Deep Learning Research - Generative Adversarial Networks - Structured Probabilistic Models for Deep Learning |
| 第 10 週 | 1. Value Based Reinforcement Learning 2. Deep Learning Research - Approximate Inference - Restricted Boltzmann Machines |
| 第 11 週 | 1. [Lab] Generative adversarial networks 2. Policy-based Reinforcement Learning |
| 第 12 週 | Paper & project proposal presentation |
| 第 13 週 | 1. [Lab] Deep Reinforcement Learning 2. [Lab] Deep Reinforcement Learning |
| 第 14 週 | Paper presentation |
| 第 15 週 | Paper presentation |
| 第 16 週 | Paper presentation |
| 第 17 週 | Final Exam |
| 第 18 週 | Final Project Presentation (TBD) |
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