人工智慧導論
Introduction to Artificial Intelligence
| 節 | 週二 |
|---|---|
3 10:10–11:00 | 人工智慧導論 EE208 3 節連堂 |
4 11:10–12:00 | |
N 12:20–13:10 |
* 根據陽明交大上課時間表所列
This introductory course provides a comprehensive overview of Artificial Intelligence (AI) with a specific focus on Computer Vision (CV) and Natural Language Processing (NLP). Designed for students without prior experience in AI, this course aims to establish a strong foundation in the fundamental concepts, techniques, and applications of AI, paving the way for advanced studies in generative AI models. Through lectures, hands-on labs, and projects, students will gain practical skills and theoretical insights necessary to understand and work with AI technologies. 這堂課程提供了對人工智慧(AI)的全面概視,特別關注於電腦視覺(CV)和自然語言處理(NLP)。課程設計針對無AI經驗的學生,旨在建立堅實的基礎,涵蓋AI的基本概念、技術和應用,為進階的生成人工智慧模型學習鋪路。透過課程講授、動手實驗和期末專題,學生將獲得實踐技能和理論能力,以理解和運用AI技術。
Python (recommended)/C++, Probability, Calculus, Linear Algebra
Midterm: 30% Homework: 65% (5 with 13 pts each) Class Participation: 5%
| 週次 | 主題 |
|---|---|
| 第 1 週 | [Course Overview] -Overview of AI, its history, and evolution -Distinctions between AI, Machine Learning (ML), and Deep Learning (DL) |
| 第 2 週 | [Fundamentals of Machine Learning] -Core concepts: supervised vs. unsupervised learning -Introduction to key algorithms: regression, classification, and clustering |
| 第 3 週 | Mid-Autumn Festival |
| 第 4 週 | [Neural Networks Basics] -Architecture of neural networks, perceptrons -Activation functions and backpropagation fundamentals |
| 第 5 週 | Hands-on Tutorials on PyTorch |
| 第 6 週 | [Deep Learning in Practice] -Theoretical Foundations: Review of key deep learning concepts, such as loss functions, optimization algorithms, and regularization techniques. -Introduction to PyTorch: Getting started with PyTorch, basic tensor operations; building and training a simple neural network model in PyTorch. |
| 第 7 週 | [Introduction to Computer Vision] -Understanding image data, pixel representations -Basic image processing: filtering, transformations |
| 第 8 週 | [Advanced Computer Vision] -Convolutional Neural Networks (CNNs) for image classification -Practical applications of CNNs |
| 第 9 週 | [Object Detection and Image Segmentation] -Techniques for object detection: R-CNN, YOLO -Image segmentation methods: semantic vs. instance segmentation |
| 第 10 週 | [Midterm] |
| 第 11 週 | Introduction to Natural Language Processing -Text processing: tokenization, stemming, lemmatization -Vector space models: from TF-IDF to word embeddings |
| 第 12 週 | [Deep Learning for NLP] |
| 第 13 週 | [Self-Supervised Learning] |
| 第 14 週 | [Graph Neural Networks (GNNs)] -Introduction to graph theory basics and GNN concepts. -Applications of GNNs: Using GNNs for node classification, link prediction, and graph classification. |
| 第 15 週 | [Reinforcement Learning] |
| 第 16 週 | [Ethics and Threats of AI] |
Eli Stevens, Luca Antiga, and Thomas Viehmann. Deep Learning with PyTorch.
- 地點
- ED-807 or after class
- 時間
- 13:10-14:00 every Tuesday
- 聯絡方式
- TEL: (03) 5712121#54530 EMAIL: hhshuai@nycu.edu.tw