ACIT4620 Computational Intelligence: Theory and Applications Course description

This course will cover fundamentals of computational intelligence (CI) techniques - modern approaches to artificial intelligence (AI), as well as several advanced topics such as adaptive-network-based fuzzy inference systems (ANFIS) and neuro-evolution. The main topics include definitions of AI and CI, history of AI and CI, symbolic vs. connectionist AI methods, mainstream CI approaches (artificial neural networks, fuzzy systems and evolutionary computation), and some representative applications of CI. The course will illustrate those CI approaches using various application examples in engineering, biomedicine and business. In addition, recent research trends, opportunities and challenges in the CI field will be discussed.

The recommended prior knowledge: Basic knowledge in calculus, statistics and probability theory; Programming skills in Python, R or Matlab

Learning Outcomes

Students are expected to have the following learning outcomes in terms of knowledge, skills and general competence.

Knowledge

On successful completion of the course, the students have:

• an in-depth understanding of state of the art Computational Intelligence (CI) methods (fuzzy sets and systems, artificial neural networks, evolutionary computation, and parts of machine learning).

• knowledge and understanding of open problems and future trends in the CI field.

Skills

On successful completion of the course, the students can:

• apply appropriate CI models and algorithms to address modeling and optimization problems in real-world applications.

• analyze complex and uncertain datasets with CI algorithms.

General competence

On successful completion of the course, the students can:

• implement CI algorithms by programming.

• deploy CI systems/models in real-world applications.

• solve complex optimization or decision-making problems using evolutionary algorithms.

The course consists of lectures, seminars and group discussions on methods and algorithms, as well as a project to be carried out in groups. The project will be chosen from a list of available research problems. The students will work in groups and will submit the code and a project report.

Practical training

Lab sessions.

The following requirements must be met before the student can take the final exam:

• One individual oral presentation on a given topic.
• Participate as discussant for two student presentations."

The assessment will be based on a portfolio of the following:

• A group project implementation, consisting of a project report (4000-8000 words) and code appendix
• An individual oral examination (about 20 min for each student)

The weight for the two parts is 50% each.

The project report should be between 4000-8000 words. Both the code/program and the report will be evaluated. The comprehensiveness of the code/program is evaluated under the assumption that each student in the group has worked on the project for 60 hours.

The portfolio will be assessed as a whole and the exam cannot be appealed.

New/postponed exam

In case of failed exam or legal absence, the student may apply for a new or postponed exam. New or postponed exams are offered within a reasonable time span following the regular exam. The student is responsible for applying for a new/postponed exam within the time limits set by OsloMet. The Regulations for new or postponed examinations are available in Regulations relating to studies and examinations at OsloMet.

For the oral exam, students will not have access to computers or other aids.

For the final assessment a grading scale from A to F is used, where A denotes the highest and E the lowest pass grade, and F denotes a fail.

Two internal examiners. External examiner is used periodically.

Professor Jianhua Zhang