機器學習

臺北科技大學 115-1 學期課程，課號 366989。

課程大綱

This course introduces the concepts, techniques, and applications of machine learning. Topics mainly include Symbolists (e.g., Decision Tree), Connectionists (e.g., Artificial Neural Networks), Bayesians (e.g., Hidden Markov Model), Analogizers (e.g., kNN), and Evolutionaries (e.g., GA), Natural Language Processing and Speech Recognition. The lecture format will be a combination of slide presentation, chalk talk and computer demonstration. In addition to the theoretical study, students are guided to survey the related references, discuss and brainstorm by group, and conduct the practice projects, so that the capability of creativity and innovation can be developed during the course.

課程進度

1. Introduction to Machine Learning (1hr) 2. Supervised Learning, e.g., Decision Tree, NB, kNN, SVM, Hidden Markov Model, and Artificial Neural Networks (9hr) 3. Unsupervised Learning, e.g., K-means Clustering, Hierarchical Clustering (9hr) 4. Machine Learning with WEKA (9hr) 5. Evolutionary Computing (8hr) 6. Natural Language Processing (5hr) 7. Speech Recognition (9hr) 8. Students' Project Presentation (4hr)

評量方式

Attendance and participation 30% Assignments 30% Oral presentation 30% Project report 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. "Data Mining - Practical Machine Learning Tools and Techniques (2nd Edition)" by Ian Witten and Eibe Frank, eBook ISBN: 9780080477022 (available in our school's library) 2. Terje Kristensen, Computational Intelligence, Evolutionary Computing and Evolutionary Clustering Algorithms. Sharjah, U.A.E.: Bentham Science Publishers. 2016 3. Dong Yu and Li Deng, Automatic Speech Recognition, A Deep Learning Approach. Springer, 2015