Course detail
Computational Intelligence
FSI-9VIN Acad. year: 2027/2028 Both semester
Computational Intelligence covers a set of nature-inspired computational methodologies and approaches to address complex real-world problems to which mathematical or traditional modeling can be useless. The course introduces basic approaches and advance methods used in the field. Practical use of the methods is demonstrated on solving simple engineering problems. Students will be given time to practice of own optimization tasks.
Language of instruction
Czech
Supervisor
Department
Entry knowledge
The knowledge of basic relations of the optimization and statistics.
Rules for evaluation and completion of the course
Submitting and defence the project which present/uses implementation of selected CI method.
The attendance at lectures is recommended. Education runs according to individual schedules. The form of compensation of missed seminars is fully in the competence of the tutor.
Aims
To give students knowledge of Computational Intelligence fundamentals, i.e. of fundamentals of nature-inspired approaches to solving hard real-world problems. Namely of fundamentals for solving of optimization problems, mathematical models and classification. The various evolutionary algorithms, optimization metaheuristics and artificial neural networks will be presented.
Understanding of basic methods of Computational Intelligence and ability of their implementation.
The study programmes with the given course
Programme D-APM-P: Applied Mathematics, Doctoral, compulsory-optional
Type of course unit
Lecture
20 hours, optionally
Syllabus
The course is divided into four thematic blocks:
Block 1: Computational Intelligence and Its Applications in Modern Artificial Intelligence. The role of computational intelligence in the context of AI and machine learning. Overview of current methods, trends, and application areas. Formulation of optimization, prediction, and classification problems. Presentation and selection of individual student projects.
Block 2: Evolutionary Computation, Swarm Intelligence, and Optimization Metaheuristics. Genetic algorithms, grammatical evolution, genetic programming, differential evolution, HC12 optimization algorithms, particle swarm optimization (PSO), and ant colony optimization (ACO). Multi-objective optimization, hybrid optimization methods, and their practical applications.
Block 3: Artificial Neural Networks and Deep Learning. Feedforward, convolutional, recurrent, and self-organizing neural networks. Modern deep learning architectures, Transformer models, and generative artificial intelligence. Transfer learning, neural network optimization, and the integration of evolutionary and neural approaches.
Block 4: Practical Applications of Computational Intelligence. Individual student projects, selection of appropriate methods, implementation, parameter optimization, and experimental evaluation of results. Algorithm comparison, result interpretation, individual consultations, and presentation of solutions.