NAS 511- Artificial Intelligence Methods in Engineering

Course Code and Name

NAS 511- Artificial Intelligence Methods in Engineering

Term

Fall, 2017-2018

Instructor

Assistant Professor Aytuğ ONAN

E-mail

aytug.onan@cbu.edu.tr

aytugonan@gmail.com

Course Day and Time

Friday, 13.15-16.00

Course Website

http://aytugonan.cbu.edu.tr/NAS511_index.html

Objectives

§  Learn the most common supervised and unsupervised ML methods, including an intuitive understanding of the algorithms, their strengths and weaknesses, and how and when to use them.

§  Learn how to choose good questions and data for ML problems, and how to interpret and evaluate the results of an ML application.

§  Install the Waikato Environment for Knowledge Analysis (Weka) toolkit and become familiar with the Explorer interface.

§  Learn to use Weka to apply several supervised and unsupervised ML methods.

§  Explore some of the current research and advances in machine learning.

Tentative Course Outline

Week#1: Introduction to machine learning, Introducing Weka

Week#2: Decision trees

Week#3: Evaluation methods, instance-based classification

Week#4: Rule-based classification

Week#5: Naïve Bayes algorithm

Week#6: Support vector machines

Week#7: Neural networks

Week#8: Unsupervised learning

Week#9: Unsupervised learning

Week#10: Project presentations

Week#11: Project presentations

Week#12: Project presentations

Week#13: Project presentations

Week#14: Project presentations

Textbook

Witten, I. H., Frank, E., Hall, M. A., & Pal, C. J. (2016). Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann.

Supplementary Materials

Kuncheva, L. I. (2004). Combining pattern classifiers: methods and algorithms. John Wiley & Sons.

Evaluation

Research Project: 100%

This will be a  project involving choosing an interesting machine learning question, finding relevant data, using Weka to answer the question, writing it up, and presenting it to the class. This can be done as an individual.