Applied Machine Learning

Serial Number
18395
Course Number
EnvE7097
Course Identifier
541 M0820
No Class
3 Credits
Elective
GRADUATE INSTITUTE OF ENVIRONMENTAL ENGINEERING
- GRADUATE INSTITUTE OF ENVIRONMENTAL ENGINEERING
Ta Fu Dave, Kuo
- View Courses Offered by Instructor
- COLLEGE OF ENGINEERING GRADUATE INSTITUTE OF ENVIRONMENTAL ENGINEERING
Fri 7, 8, 9
環工101
Type 3
The first week after the classes begin: Students register the courses and the courses will be allocated based the students' preference order. The second week after the classes begin: Students add the courses online with the given permission number.
30 Student Quota
NTU 30
No Specialization Program
English
NTU COOL
Core Capabilities and Curriculum Planning

Notes
The course is conducted in English。
NTU Enrollment StatusNTU students only. Updated every five minutes during the course selection period.
Enrolled
0/30
Other Depts
0/0
Remaining
0
Registered
0
Course Description
Introduction to machine learning (ML): core elements and terminologies, underlying mathematical philosophy, solution categories, general work-flow of ML solutions development, and examples of ML-based solutions in various domains. Cover the mathematical bases and algorithms of various supervised and unsupervised learning methods. Discuss and develop ML strategies for selecting/assessing the right ML approach for a given environmental science or environmental engineering problem.
Course Objective
Theory and practice of implementing machine learning (ML) techniques for problems in environmental science and engineering. Discuss the inner workings of various ML algorithms: k-nearest neighbors (k-NN), naïve Bayes, decision trees, artificial neural network (ANN), support vector machines (SVM), k-means clustering, recurrent neural network (RNN), and convolutional neural network (CNN), and more. Emphasis on practical application and techniques with real environmental problems and data.
Course Requirement
No prerequisites.
Expected weekly study hours before and/or after class
Office Hour
*This office hour requires an appointment
Designated Reading
待補
References
Marsland, S. 2015, Machine Learning – An Algorithmic Perspective, CRC Press. Flach P. 2012, Machine Learning, Cambridge.

Grading

15%	Quizzes Weekly quizzes (~15 min) at the beginning of each lecture, starting from Week 2
25%	Assignments Weekly to bi-weekly assignments
30%	Term Project Written report on application of ML methods to environmental science / engineering problems of choice.
30%	Mid-terms 2 mid-terms

Adjustment methods for students
Make-up Class Information

Course Schedule

Week 1		Introduction + Navigating in Python
Week 2		Preliminary to ML
Week 3		Perceptron
Week 4		Multi-Layer Perceptron
Week 5		Radial Basis Functions + Data Tidying
Week 6		Mid-term (I)
Week 7		Dimensionality Reduction
Week 8		Probabilistic Learning
Week 9		Support Vector Machine + Evolutionary Learning
Week 10		Reinforcement Learning + Tree Based Methods
Week 11		Tree Based Methods + Ensemble Learning
Week 12		Mid-term (II)
Week 13		Unsupervised Learning
Week 14		Markov Chain Monte Carlo (MCMC) Methods
Week 15		Graphical Methods
Week 16		Miscellaneous Topics & Conclusion