資料探勘研究與實務
Data Mining Research & Practice
| 節 | 週四 |
|---|---|
A 18:30–19:20 | 資料探勘研究與實務 MB311（光復） 3 節連堂 |
B 19:30–20:20 | |
C 20:30–21:20 |
* 根據陽明交大上課時間表所列
The main objective of this class is to study techniques and applications of data mining, drawing work from areas including database technology, artificial intelligence, and knowledge-based systems. This course will cover Hadoop, MapReduce and Data Mining, as well as some topics related to Text Mining and Recommender Systems. Students are required to accomplish project assignments on the implementation and experiment on mining data from various application domains.
google meet for online class https://meet.google.com/nhm-igtz-jsp
無備註
Reference: Data Mining: Practical Machine Learning Tools and Techniques, Morgan Kaufmann, 2017, Ian H. Witten, Eibe Frank, Mark A. Hall, Christopher J. Pal Tensforflow+Keras深度學習人工智慧實務應用,博碩,林大貴著2017年 Python+Spark 2.0+Hadoop 機器學習與大數據分析實戰,博碩,林大貴著2016年9月 Introduction to Information Retrieval, Cambridge University Press, 2008, Christopher D. Manning, Prabhakar Raghavan, Hinrich Schutze (http://nlp.stanford.edu/IR-book/)
Homework and Participation (25%), Project (15%), Midterm (30%), Final (30%)
Introduction
Overview
- 講授：
- 3
Data Preprocessing
Data cleaning Data transformation Data reduction Data discretization
- 講授：
- 3
Mining Association Rules
Mining frequent patterns Apriori algorithm Multidimensional association rules
- 講授：
- 5
Classification
Decision tree Bayesian classification Rule-based classification Neural network Support vector machines K-NN classifiers Genetic algorithm Accuracy, Precision, Recall
- 講授：
- 14
Cluster Analysis
K-means Hierarchical clustering Expectation-maximization Self-organizing Maps
- 講授：
- 6
Text Mining
Basic concepts Information retrieval Vector Space Model Language Model
- 講授：
- 6
Recommender Systems
Content-based approach Collaborative-filtering Hybrid approach Matrix factorization
- 講授：
- 6
Link Analysis and Social Network Analysis
Social Network Analysis HITS, PageRank Ontology-based network analysis
- 講授：
- 3
Deep Learning
Convolutional neural networks (CNNs) Recurrent neural networks (RNNs) LSTM
- 講授：
- 5
Big data Analytics
Big Data – Platform and Analytics Hadoop, MapReduce, Spark
- 講授：
- 3
| 週次 | 主題 |
|---|---|
| 第 1 週 | Introduction; Data Preprocessing |
| 第 2 週 | Classification and Prediction |
| 第 3 週 | Classification and Prediction |
| 第 4 週 | Cluster Analysis |
| 第 5 週 | Text Mining and Information Retrieval |
| 第 6 週 | Text Mining and Information Retrieval |
| 第 7 週 | Recommender Systems |
| 第 8 週 | Big Data – Platform and Analytics – Hadoop, MapReduce |
| 第 9 週 | Convolutional neural networks (CNNs), Recurrent neural networks (RNNs), LSTM |
| 第 10 週 | Midterm |
| 第 11 週 | Recommender Systems |
| 第 12 週 | Classification and Prediction |
| 第 13 週 | Classification and Prediction |
| 第 14 週 | Clustering |
| 第 15 週 | Link analysis and Social Network Analysis |
| 第 16 週 | Mining Association Rules, Sequential pattern |
| 第 17 週 | Mining Association Rules, Sequential pattern |
| 第 18 週 | Final exam |
Introduction to Data Mining, 2nd, Pearson, 2019, Pang-Ning Tan, Michael Steinbach, Anju Karpatne and Vipin Kumar (https://www-users.cs.umn.edu/~kumar001/ dmbook/index.php) Data Mining: Concepts and Techniques, 3rd ed., Morgan Kaufmann Publishers, 2011, by Jiawei Han, Micheline Kamber and Jian Pei (Course slides: http://web.engr.illinois.edu/~hanj/bk3/) Paper Readings; Competition data sets: https://www.kaggle.com/competitions scikit-learn: Machine Learning in Python http://scikit-learn.org/stable/ Links to Data Mining Software and Data Sets. URL: http://www-users.cs.umn.edu/~kumar/dmbook/resources.htm
- 地點
- MB 305
- 時間
- Thur. pm 5:30 ~ 6:30
- 聯絡方式
- dliu@mail.nctu.edu.tw