* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Download Fundamentals of Computational Intelligence
Survey
Document related concepts
Human-Computer Interaction Institute wikipedia , lookup
Concept learning wikipedia , lookup
Incomplete Nature wikipedia , lookup
Machine learning wikipedia , lookup
Type-2 fuzzy sets and systems wikipedia , lookup
Knowledge representation and reasoning wikipedia , lookup
Fuzzy concept wikipedia , lookup
Intelligence explosion wikipedia , lookup
Fuzzy logic wikipedia , lookup
Existential risk from artificial general intelligence wikipedia , lookup
Philosophy of artificial intelligence wikipedia , lookup
Transcript
ECE 457B: Fundamentals of Computational Intelligence: Approximate Reasoning and Connectionist Modeling Winter 2017 Instructor: Prof. Fakhri Karray, Office: E5 Office #5029, ext 35584, email: [email protected]. Instructor will be available throughout the term by appointment. Teaching Assistants: Name: Arief Barkah Name: Alaa ElKhatib Name: Chaojie Ou Time: Winter 2017, T, Thu: 2:30 pm-3:50 pm (lectures), Tutorials on Thursday 7pm:7:50pm: first session January 12, 2017 Location: Lectures: Room# RCH-101; Tutorials: Room# RCH-301 Course Description: The course introduces novel concepts in computational intelligence based techniques. It includes concepts on knowledge based reasoning, fuzzy inferencing systems, connectionist modeling based on artificial neural networks, and deep learning. The course material is self-contained but could be used as a good complement for concepts introduced in ECE457A. The course focuses mainly on the use of soft computing approaches to deal with real world complex systems for which mathematical models may be hard to obtain because of structural complexities, mathematical intractability and inherent uncertain behaviour. The main thrust will be on designing computationally intelligent systems with human like capabilities in terms of reasoning, learning and adaptation to changing environments. Tools of computational intelligence could be used in a wide range of engineering applications involving real world problems such as in: human-machine interaction, intelligent control, intelligent transportation systems, autonomous robotics/devices, smart mechatronics, natural speech and language understanding, pattern analysis, gaming, search, intelligent network design, communication systems to name a few. It is neither a pre-req nor an anti-req of ECE457A. It complements it. Prerequisite Material: Linear algebra, advanced calculus, discrete mathematics, Boolean algebra or equivalent, optimization. Material for the Course: All material related to the course (lectures, assignments, other pertinent documents) and updates are posted on LEARN. Course Textbooks (not mandatory): Soft Computing and Intelligent Systems Design, F. Karray and C. de Silva, Addison Wesley Pub. 2004 Computational Intelligence: A Methodical Introduction, R. Kruse, C. Borgelt, C. Braune, 2nd Edition, Springer, 2016 Machine Learning, S. Marsland, 2nd Edition, CRC Press, 2015 Artificial Intelligence, M. Negnevitsky, Addison Wesley, 2005 Other pertinent readings will be posted regularly on the course website on LEARN. Major Topics: The course will be divided in modules. Approximate duration of various modules is provided below: 1. Introduction to soft computing and computational intelligence: overview on fuzzy logic systems, neural networks, probabilistic reasoning, approximation and intelligence (one week) 2. Fuzzy Logic systems: Notion of fuzzy set, generalized fuzzy operations, fuzzy relations (two weeks) 3. Composition and inferencing, fuzzy logic decision based systems (two weeks) 4. Fundamentals of connectionist modelling: learning and acquisition of knowledge, features of neurocomputing; supervised vs unsupervised, reinforcement learning (one week) 5. Major classes of artificial neural networks: multiLayer perceptron, kernel based networks, self organizing Map, Hopfield neural networks, auto associative memory (four weeks) 6. Introduction to deep learning and applications (one week) Course Marking Scheme: Assignments (12%): Three marked assignments. Submission of the assignments is mandatory. Any missed assignment will lead to a grade of INC for the course. Design Project (33%):Project will be carried out by groups of students. Main themes: driverless vehicles, intelligent machines, and Alexa Virtual Assistant. Abstract due on January 19. Final report and poster presentation due around the last two weeks of the term. Details will be posted throughout the term on LEARN. Final (55%): Date and location assigned by Registrar office sometime in April, 2017