深度學習應用開發實務

臺北科技大學 114-2 學期課程，課號 357410。

課程大綱

The goal of this course is to give students a broad overview of state-of-the-art deep learning algorithms, and teach students how to develop deep learning applications by hands-on coding examples. Most examples taught in this class are based on the TensorFlow framework. We will cover many different fields including image classification, object detection, natural language processing, reinforcement learning and generative adversarial networks.

課程進度

Course website: http://www.aiotlab.org/teaching/dl_app.html 1. Introduction to Deep Learning 2. Applied Math (Linear Algebra, Probability, Calculus) 3. Machine Learning Basics 4. TensorFlow & Keras 5. Convolutional Neural Networks (CNN) 6. Advanced Keras API & PyTorch 7. Natural Language Processing (NLP), Word Embedding, Self-supervised Learning 8. Midterm exam 9. Recurrent Neural Networks (RNN) & Long Short-term Memory (LSTM) 10. Attention is all you need! Attention and Transformer 11. Large Language Models (LLMs), ChatGPT, Gemini, DeepSeek 12. Retrieval Augmentation Generation (RAG) 13. Object Detection and Segmentation 14. Generative Adversarial Networks (GAN) and Diffusion models 15. Deep Reinforcement Learning and Stable Baseline 16. Graph Convolution Networks (GCNs) 17. Final project demo 18. Final exam

評量方式

Homework (40%), Midterm and Final Exam (35%), Final Project (15%), Quizzes and attendance (10%)

教材

【遵守智慧財產權觀念，請使用正版教科書，不得使用非法影印教科書】 使用外文原文書：是 1. Francois Chollet, “Deep Learning with Python, 2nd edition” Manning, 2021 2. Ian Goodfellow, Yoshua Bengio, and Aaron Courville, “Deep Learning,” MIT Press, 2017 3. Latest publications on CVPR, NIPS, ICML, AAAI, ICLR Website: http://www.aiotlab.org/teaching/dl_app.html