ACIT4620 Computational Intelligence: Theory and Applications Course description

Computational Intelligence is concerned with modern, bio-inspired approaches to artificial intelligence (AI) and is an umbrella term for the fields of neural networks (NN), fuzzy systems (FS) and evolutionary computation (EC). This course offers a comprehensive and systematic introduction to the fundamental concepts, principles, and methods in the three fields, a part of machine learning and deep learning, and several advanced topics (neuro-fuzzy systems, neuro-evolution, or fuzzy clustering). The course will illustrate major CI concepts, principles and methods using various application examples in engineering, biomedicine and business. In addition, the overview, history, state-of-the-art, and future trends of AI and CI field will be covered. The main modules for lectures include:

• AI and CI: Overview and history
• Fundamentals of neural networks
• Introduction to deep learning
• Fuzzy sets, logic and systems
• Topics in evolutionary computation
• Advanced topics
• AI and CI: State-of-the-art and future

It is recommended that students have some background knowledge in:

1) mathematics: calculus, linear algebra, statistics and probability theory, and numeric optimization

2) programming language in Python, Matlab or R

3) machine learning and/or data mining.

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 overview on different perspectives, history and future of AI and Computational Intelligence (CI) fields.
• familiarity with the essential terminologies, concepts, ideas, elements and principles in the three pillar fields of CI.
• an in-depth understanding of state-of-the-art CI methods (fuzzy systems, neural networks, evolutionary computation, deep learning, and hybrid AI techniques).
• knowledge and understanding of open problems and future challenges and opportunities in the AI and CI field.

Skills

On successful completion of the course, the students can:

• determine when to use and deploy the CI methods learned for real-world applications.
• 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:

• program the CI models/algorithms.
• deploy CI systems/models in real-world applications.
• solve complex search, optimization or decision-making problems using evolutionary algorithms.

The course consists of lectures (theory), labs (practical exercises and computer simulations/experiments), group discussions, Q&As, as well as group projects. The group projects will be assigned from a list of the suggested topics/areas. The students will work in groups and finally submit the project report as well as the code.

Practical exercises: Lab and Q&A sessions.

The following two group assignments must be approved before the student can take the final exam:

• 1 - Group report and presentation: Group written report and oral presentation on the assigned topic.
• 2 - Group project proposal: A group project proposal (1000 - 1200 words) on the assigned topic, containing project description, the available dataset(s), method/algorithm to be employed, and references (including several most recent journal publications).

The final exam consists of two parts:

• Part 1 - Group project report with code: A group (2-4 students) project implementation, including a project report (5000 - 7000 words, excluding references) and code as an appendix (counts 50% towards the final grade). Both the code and the report will be evaluated. The comprehensiveness of the code is evaluated under the assumption that each member of the group has worked on the project for 60 hours.
• Part 2 - Individual written exam: An individual, closed-book, written exam (3 hours) (counts 50% towards the final grade)

Both parts must be passed in order to pass the course (i.e., if a student fails in one part, he or she would automatically fail the course).

The exam results can 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 registering 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.

All aids are permitted for the group project, provided the rules for plagiarism and source referencing are complied with (Exam - Part 1).

For the closed-book, individual written exam (Exam - Part 2), students will work on a computer in an exam room (with invigilators), can use pen and a simple, non-programmable calculator, but will not have access to Internet, books, notes or other aids.

Grade scale: A-F.

Two examiners. External examiner is used periodically.

Professor Jianhua Zhang