用Python於深度學習
Lab on Python for Deep Learning
| 節 | 週三 |
|---|---|
5 13:20–14:10 | 用Python於深度學習 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
This course following a challenge-based learning (CBL) framework, and classes will be fully online We will use slack to communicate to the class. Please add yourself here: https://labonpythonfo-hqk1541.slack.com/archives/C08DZ86N1DX make sure you turn on the notifications The calendar event is here, please to add it to your schedule: https://calendar.google.com/calendar/event?action=TEMPLATE&tmeid=N2JhOGR0Z3ZvcGp1YTA4a[...]ByaW5pLnN0ZWZhbm9AbQ&tmsrc=rini.stefano%40gmail.com&scp=ALL Meeting Link: https://meet.google.com/qcd-mtke-axd The class will follow the schedule of this class: https://harvard-iacs.github.io/2021-CS109B/pages/schedule.html you can review the slides ahead of class here: https://github.com/Harvard-IACS/2021-CS109B/tree/master/docs/lectures
Basic programming skills on Python
This class is based on challenge-based learning a detailed document describing the challenge based learning framework is here: https://docs.google.com/document/d/17dSTVl4BYoR_yUmA660ZVqIMH3tTMFvXO0vk5-2EBQs/edit?tab=t.0#heading=h.6e9ngz5jsy63
NO EXAM Phase 1: 25% The score is obtained as the sum of scores from cross-team evaluation and the elevator pitch, assigned to each student proportionally to the intra-team evaluation of each member. Phase 2: 35% The score is obtained as the sum of score from cross team evaluation and the elevator pitch, equally divided across the team members Phase 3: 40% The score is provided by the professor and divided equally across the team members.
| 週次 | 主題 |
|---|---|
| 第 1 週 | Course Introduction, Splines, Smoothers, and GAMs |
| 第 2 週 | Splines, Smoothers, and GAMs, Unsupervised Learning: Cluster Analysis |
| 第 3 週 | Unsupervised Learning: Cluster Analysis, Bayesian Statistics |
| 第 4 週 | Bayesian Statistics |
| 第 5 週 | Bayesian Statistics and Hierarchical Models |
| 第 6 週 | CNNs Basics, Pooling, and CNNs Structure |
| 第 7 週 | Intercollegiate activities (holiday) |
| 第 8 週 | Backpropagation, Receptive Fields and Feature Map Visualization |
| 第 9 週 | Saliency Maps, State-of-the-Art Models (SOTA) and Transfer Learning |
| 第 10 週 | RNNs, GRUs, and LSTMs |
| 第 11 週 | Language Modeling (NLP) and Word Embeddings |
| 第 12 週 | Transformers and Autoencoders |
| 第 13 週 | Transformers and Variational Autoencoders (VAE) |
| 第 14 週 | Generative Adversarial Networks (GANs) |
| 第 15 週 | GANs and Deep Reinforcement Learning |
| 第 16 週 | Final Presentation |
An Introduction to Statistical Learning by James, Witten, Hastie, Tibshirani (Springer: New York, 2013) Deep Learning by Goodfellow, Bengio and Courville. (The MIT Press: Cambridge, 2016) Deep Learning, Vol. 1 & 2 by Andrew Glassner Speech and Language Processing by Jurafsky and Martin (3rd Edition Draft) Introduction to Natural Language Processing by Jacob Eisenstein (The MIT Press: Cambridge, 2019)
- 地點
- Online
- 時間
- By appointment via Slack.
- 聯絡方式
- rini.stefano@gmail.com