By the end of this course, students should possess a firm grounding in the existing techniques and key component areas of Artificial Intelligence and be able to apply this knowledge to the development of Intelligent Systems and/or to the exploration of research problems.

• Understand what Artificial Intelligence is about and appreciate its relevance to Computer Science and importance for IT and society.
• Understand the principles of problem solving and of the state space search approach, be able to efficiently formulate a problem and evaluate its complexity, master various search algorithms, and be capable of selecting and applying these techniques appropriately.
• Be familiar with techniques for computer-based representation and manipulation of complex information and knowledge, understand formal logic inference and reasoning algorithms, and be able to employ these tools to build knowledge-based systems
• Understand the issues underlying problems of partially known or uncertain information, master the fundamentals of probabilistic reasoning, be able to employ belief networks to model real-world problems, and be able to develop decision-theoretic systems.
• Gain awareness of several advanced AI applications and topics such as intelligent agents, constraint satisfaction, game playing, applied expert systems, approximate reasoning, machine learning, etc.

For more information, please log in to edveNTUre.

Topics covered in this course:

• Computational Intelligence overview, sources of inspiration, types of adaptive (learning) systems, types of applications.
• Visualization and exploratory data analysis: few variables, direct virtualization, Principal Component Analysis (PCA), Multidimensional Scaling (MDS), Self-Organizing Mappings(SOM), parallel coordinates and other visualization algorithms.
• Model selection, evaluation of results, ROC curves + WEKA overview, Decision Tree.
• Human Brain - Congnition, Symbolic Knowledge Representation, Cognitive Architecture.
• Overview of Learning Systems

For more information, please log in to edveNTUre.

This course gives an introduction to basic neural network architectures and learning rules. Emphasis is placed on the mathematical analysis of these networks, on methods of training them and on their application to practical engineering problems in such areas as pattern recognition, function approximation and signal processing.

For more information, please log in to edveNTUre or visit http://www.c2i.ntu.edu.sg/Courses/NN/details/nn/