With the recent development of AI technology, AI technology has largely affected the electrical engineering (EE) field, and active researches and developments are being conducted. Nowadays, knowledge of AI and machine learning becomes essential for EE students.

This course aims at covering a wide range of the machine learning field from basic classical machine learning theories and applications for solving data-based engineering problems to the latest deep learning-based learning techniques.

- Prerequisites (strongly preferred): 신호및시스템, 선형대수, 확률 및 통계

Exam: Attendance (10%), Mid-term exam(30%), Final project (40%), PAs (20%)

Marc P. Deisenroth et al., "Mathematics for Machine Learning", Cambridge University Press, 2020.
Kevin P. Murphy, "Machine Learning: a Probabilistic Perspective", MIT Press, 2012.
Christopher M. Bishop, "Pattern Recognition and Machine Learning", Springer, 2006.
Goodfellow et al., "Deep Learning", MIT Press, 2016.
Richard O. Duda, Peter E. Hart, and David G. Stork, "Pattern Classification", 2nd Ed., Wiley-Interscience, 2001.
오일석 저, "패턴 인식", 교보문고, 2008.

1. Introduction to machine learning
2. Preliminaries (Linear algebra, probability and statistics)
3. Supervised learning - Simple models
4. Supervised learning - Support vector machine
5. Unsupervised learning - Clustering
6. Unsupervised learning - Density estimation
7. Unsupervised learning - Dimension reduction
8. Mid-term exam.
9. Neural networks 1
10. Neural networks 2
11. Tips for training neural networks
12-13. Generative model
14. Learning with visual data
15. Learning with multi-modal data (text and audio)
16. Final term project presentation

Lecture type: Traditional lecture
Grading: Graduate students are graded separately
Honor code: You must conduct all the HWs and PAs from scratch independently. One-strike-out policy for the honor code violations.

On PLMS