Relevance of Course Objectives and Core Learning Outcomes(%) |
Teaching and Assessment Methods for Course Objectives |
Course Objectives |
Competency Indicators |
Ratio(%) |
Teaching Methods |
Assessment Methods |
1.了解自2012年AlexNet問世迄今,深度學習技術的主要發展技術歷程與近年相關技術理論、以及相關應用。
2.了解如何執行deep learning的模型訓練、佈屬等。 |
1.Basic Knowledge in Mathematical Sciences |
4.Professional Knowledge in Scientific Computation |
|
|
topic Discussion / Production |
Networking / Distance Education |
Lecturing |
|
Written Presentation |
Oral Presentation |
Assignment |
|
Course Content and Homework/Schedule/Tests Schedule |
Week |
Course Content |
Week 1 |
Introduction to deep learning |
Week 2 |
Machine Learning Basics |
Week 3 |
Introduction to deep convolutional neural network (filter, kernel, signal processing basics) |
Week 4 |
Introduction to deep convolutional neural network (classifier-1) |
Week 5 |
Introduction to deep convolutional neural network (classifier-2) |
Week 6 |
Autoencoder, Unet, and Segmentation networks |
Week 7 |
Latent code, Deep feature tensors, and multi-dimensional scaling |
Week 8 |
Object detection networks |
Week 9 |
Take-home Midterm or Term Project Proposal |
Week 10 |
Data Augmentation Methods (1) |
Week 11 |
Long-tailed Distribution Data Classification |
Week 12 |
Data Augmentation Methods (2) |
Week 13 |
Introduction to Generative Adversarial Networks (GANs) |
Week 14 |
Introduction to Domain Adaptation and Domain Generalization |
Week 15 |
Introduction to Active Learning |
Week 16 |
Introduction to Anomaly Detection
Term Project Presentation
Term Project Presentation |
self-directed learning |
|
|
Evaluation |
By default: Homework (25%*3) + Term-Project/Report (25%)
If necessary, we can still make some modification. |
Textbook & other References |
Goodfellow et al., ”Deep Learning”, web-version available. |
Teaching Aids & Teacher's Website |
|
Office Hours |
預約 |
Sustainable Development Goals, SDGs(Link URL) |
| include experience courses:N |
|