Perceptrons, multi-layer perceptrons, recurrent neural networks, genetic algorithms, differential evolution, particle swarm intelligence, ant colony optimization.

Course Objectives

To introduce students to the fundamentals and applications of computational intelligence techniques inspired by natural systems, including neural networks, evolutionary algorithms, and swarm-based optimization. The course aims to equip students with the skills to model, analyze, and solve complex problems using biologically inspired computational approaches.

Recommended or Required Reading

Kruse, R., Borgelt, C., Braune, C., Mostaghim, S., Steinbrecher, M., Klawonn, F., & Moewes, C. (2011). Computational intelligence. Vieweg+ Teubner Verlag.

Eiben, A. E., & Smith, J. E. (2015). Introduction to evolutionary computing. springer.

Learning Outcomes:

1. To be able to explain computational intelligence and its main mechanisms.

2. To be able to identify the most appropriate computational intelligence method for a given problem.

3. To be able to apply computational intelligence methods to machine learning and optimization problems.

4. To be able to design experimental studies for computational intelligence algorithms.

Grading:

• Midterm Exam %50
• Final Exam %50

Submissions: Project, Report

Supplementary course: CENG 504, CENG 506