資料科學

Data Science

學期

114-2

學分

3 學分

當期課號

535105

永久課號

EEEE30026

開課單位

人工智慧跨域學程-工程與科學組、智能系統研究所、電機工程學系

授課教師

江孟芬

校區

光復

類別

選修

上課時間表

節	週四
5 13:20–14:10	資料科學 EDB26（光復） 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

概述

This course provides a comprehensive introduction to data science, covering: • Natural Language Processing (NLP): A review of the evolution of text processing, from linguistic fundamentals to modern language modeling. • Mathematical Foundations: A review of essential Probability and Linear Algebra required for understanding high-dimensional data and machine learning algorithms. • Learning with Graphs: Exploration of graph-based learning methods to identify patterns and perform predictive analysis on networked data. • Scalable Data Structures & Algorithms: Study of efficient data management through Hashing and the processing of Data Streams. • Practical Implementation: Hands-on experience through programming assignments that translate theoretical concepts into functional code. • Research Project: Development of professional research skills through a collaborative group project, learning a formal research presentation.

先修科目

Probability, Proficiency in Python, Foundations of Machine Learning

備註

無備註

教學方式

教師未提供此項資料

評分方式

• 3 Individual Assignments: 45% • Final Exam: 35% • Final Research Project: 30%

課程大綱

教師未提供此項資料

週次計畫

週次	主題
第 1 週	Introduction to Data Science
第 2 週	Natural Language Processing (I) * Transformer
第 3 週	Natural Language Processing (II) * Pre-Training * [A1: 15% Release]
第 4 週	Natural Language Processing (III) * Post-Training * Alignment
第 5 週	Natural Language Processing (IV) * Language Agent
第 6 週	Fundamentals of Linear Algebra
第 7 週	Learning with Graphs (I) * Link Analysis * [A2: 10% Release]
第 8 週	Learning with Graphs (II) * Graph Representation Learning * [GP: Research Topics Due]
第 9 週	Learning with Graphs (III) * Graph Foundation Model
第 10 週	Hashing (I) * Universal Hashing * Locality-Sensitive Hashing * [A3: 10% Release]
第 11 週	Hashing (II) * Approximate Nearest Neighbor Search
第 12 週	Data Stream (I) * Bloom Filter * Sampling Techniques
第 13 週	Data Stream (II) * Data Stream Algorithms
第 14 週	Final Exam [35%]
第 15 週	Research Project Oral Presentation
第 16 週	Research Project Oral Presentation * [GP: 30% Report Due]

教科書

Leskovec, J., Rajaraman, A., & Ullman, J. D. (2020). Mining of Massive Datasets (3rd ed.). Cambridge University Press.

Office Hours

地點: EDB26[GF]
時間: R567
聯絡方式: 教師未提供此項資料