Computational Intelligence: Theory and Applications

Computational Intelligence is concerned with modern bio-inspired paradigm 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 core concepts, principles, and methods in neural networks, fuzzy sets and systems, deep learning, complex networks, and several advanced topics (neuro-fuzzy systems, fuzzy clustering, etc.). 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 field will be covered at the beginning of the lectures. 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
• Hybrid AI - Neuro-fuzzy systems
• Web intelligence - Complex networks
• AI and CI: State-of-the-art and future

Language of Instruction: English

It is recommended that students have some background knowledge or taken preliminary/introductory courses in:

1) engineering 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 paradigms, history and future of AI and Computational Intelligence (CI) fields.
• familiarity with the key terminology, concepts, elements and principles in the main CI approaches.
• an in-depth understanding of state-of-the-art CI methods (fuzzy rule-based systems, neural networks, deep learning, complex networks, and hybrid AI techniques).
• knowledge and understanding of 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 for real-world applications.
• apply appropriate CI models and algorithms to modeling, pattern recognition, optimization, decision-support and control problems in real-world applications.
• analyze large-scale, complex, uncertain data with CI models and 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 system related problems using the theory of complex networks.

The course consists of lectures (theory), labs (practical exercises, computer simulations/programming, and software implementation), group discussions as well as group projects. Each group project will be assigned certain topics/areas. The students will work in groups and finally submit the project report alongside the code.

Practical exercises: Lab and Q&A sessions.

The following mandatory assignment must get approved before the student is entitled to take the final exam:

• Group project proposal (groups of 3-5 students): 1000- 200 words on the assigned topic, containing description of the project ideas, the available dataset(s), model/algorithm to be employed, and references (including several most recent journal publications).
• Literature overview and analysis: Based on the assigned topic and their proposal, the students are required to search for, read through, understand and analyze a recent journal paper. Then they will summarize and write up the key content of the paper they read.

The final exam consists of two parts:

• Part 1 - Group project report with code (groups of 3-5 students): A group 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, 3 hours, (counts 50% towards the final grade)

Both parts must be passed in order to pass 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.

Part 1: All aids are permitted for the group project, provided the rules for plagiarism and source referencing are observed.

Part 2: students 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.

One internal examiner

External examiners are used periodically. 

Professor Jianhua Zhang