Course information

A. Introduction to the basic principles of development and operation of Artificial and Computational Intelligence systems. Summary of centralized and distributed intelligence. Knowledge (structure, representation, manipulation), reasoning, intelligent behavior. Presentation of the structure, operation and exploitation of modern knowledge-based software systems that allow easy integration of rules, regulations, empirical guidelines and various restrictive provisions. B. Genetic algorithms and evolutionary systems. Genetic structures and evolutionary agents. Parameters of evolutionary systems. Behavior and convergence of evolutionary systems. Optimization and other applications of evolutionary systems. Other techniques (Neural networks, Fuzzy Logic, Self-organizing systems). Fuzzy systems, meta-heuristics, artificial immune networks. C. Applications in ship design and operation. Hull shape optimization with the help of Computational Intelligence and ES. Ship systems design support. Presentation and laboratory familiarization with two expert systems that support ship loading and optimal ship routing. D. General principles of Machine Learning. Introduction to the field of machine learning-the different types. Supervised learning. Unsupervised learning. Prediction (linear, logistic regression). Support Vector Machines. Reinforcement learning. Bayesian learning. E. Deep Learning Neural Networks. Learning complex representations with data. Review. Big data. Examples of structures. Applications in technological and scientific areas. G. Programming Tools for Neural Networks. The NN/DNN toolbox in MATLAB. Modern hardware platforms.