Artificial Intelligence

Basic Concepts for logic – Language: meaning and definition – Informal fallacies – Analogy and Legal and moral Reasoning – Causality and Mill's methods – Probability and Statistical Reasoning – Hypothetical reasoning – Categorical Propositions – Categorical syllogisms – Propositional logic – Natural deduction in propositional logic – Predicate logic – Löwenheim – Skolem Theorem – Tarski semantics – Skolem-Herbrand-Gödel Theorem – Sequent calculus – Gentzen's Theorem – Church's Theorem – Gödel's Incompleteness Theorem.

Introduction – Object-oriented representation – Structured descriptions – Ontologies and representation of Domain Knowledge – Knowledge Representation in Social Context – Logic Programs – Abductive Reasoning – Qualitative Reasoning – Constraint Satisfaction – Representation of Actions – Reasoning with Actions – Practical Planning – Abstraction – Reformulation and Approximation.

Intelligent Agents: Introduction – Search based Planning – Scaling Planning for Complex Tasks – Acting in Uncertain Environments – Algorithmic – game-theoretic and logical foundations of multi-agent systems – Multi-Agent architectures – Inter-agent communication – Cooperative distributed problem solving – Collaborative plans and social systems – Multiagent learning – Distributed rational decision making – Applications in multi-robot control systems.

Probability tools – concentration inequalities – PAC model – Rademacher complexity – Growth function – VC-dimension – Perceptron – Winnow – Kernel methods – Boosting – Decision trees – Density estimation – maximum entropy model

Introduction to Data and Models – Generative and Discriminative models – Bayesian Decision Theory – Evaluation of Performance – Training of parametric models: ML – MAP estimators – EM estimation of parametric models with latent variables.

Introduction – Dualism – Cognitive Architectures – Layers of Mental Activities – Common Sense – Mind as Behavior: Behaviorism – Mind as the Brain: Mind-Brain Identity Theory – Mind as Computer: Machine Functionalism and Classical AI.

Introduction – Foundations of Inductive Learning – Concept Learning and Categorization – Controlling Complexity and Occam's Razor – Reasoning about Natural Kinds

Grammars and the Chomsky Hierarchy – Regular languages – Finite state automata (FSA) – probabilistic FSAs – Context-free languages and Push-down automata – Ambiguity and solutions to the problem – Deterministic parsers – Chart parsers – Probabilistic context-free grammars – Modelling semantics – Context-sensitive language.

Overview of clustering – Metrics spaces and coverings – Clustering in metric spaces – k-center problem – k-means problem – Hierarchical clustering – Clustering graph data and planted partition models – Linear and Non-Linear Dimensionality reduction.

Overview of reinforcement learning – Bandit problems and online learning – Markov decision processes – Returns and value functions – Solution methods: dynamic programming – Monte Carlo learning – Temporal difference learning

History of robotics – Actuators – Locomotion – Manipulation – Sensors and sensing for robotics – Sensor based and odometry Navigation – Workspace decomposition and search algorithms on graphs – Configuration Space and configuration-space obstacles

Computer organization fundamentals – Modern processor memory and peripherals design and organization – Modern computer design principles and levels of abstraction – Instruction set architecture design and implementation – Computer hardware-software interface – Computer performance-based design – Computer processor design data path and control – Instruction pipelining – Parallel computer paradigms – instruction set architectures and design – Architecture-oriented programming – Power and energy aware computing – Tools and simulation for computer design and performance enhancement.

Signals Applications – Signals Definitions and Classifications – Signals' Power and Energy – Basic Signals – Systems and Systems' Properties – Linear and Time-Invariant (LTI) Systems – Fourier series – Fourier transform for continuous and discrete time signals – Sampling theorem – Laplace transform – Z-Transform – Transfer function – State space representation – Filters design and applications.

Computational approaches to studying cognition; General motivations underlying the computational modeling of cognition – Parallel versus serial processing – Flow of information

Topics which are not included in the curriculum and seems to be needed should be suggested as an elective course by CS department.

Topics which are not included in the curriculum and seems to be needed should be suggested as an elective course by CS department.

Cognitive Robotics introduction – Cognition and the sense-plan-act architecture – Deliberative, reactive and hybrid approaches – Deliberative systems for cognitive robots – Symbolic planning and PDDL – Bioinspired controllers for autonomous robots – Behavior based architectures – Neural networks and learning – Human- Robot interaction – Non-verbal human robot interaction.

Overview of Biometrics – Performance Evaluation and Comparison of Biometrics – Overview of Image Processing / Edge Detection in Digital Images – Fingerprint Recognition – Face Recognition – Iris Recognition – Hand Shape Recognition – Voice Recognition – Multi-modal Biometric Systems – Biometric System Security – Identity Science Technology – Issues of privacy.

Introduction to Brain-Computer Interfaces, Basic Neuroscience – Recording/ Stimulation Techniques – Signal Processing and Machine Learning for BCI – Invasive BCIs. Neural Prosthetics – Decoding using Bayesian Filtering – Cognitive Control – Volitional control of neural activity and bidirectional neural interfaces – Semi-Invasive BCIs with Electrocorticography (ECoG) – Nerve-Based Approaches – Evoked Potentials (SSVEP and P300) – Restoring Sensory and Motor Function – Security – Cognitive Monitoring – and Entertainment – BCI Applications in Robotic Avatars and Image Search.

Introduction – Computation – Information – Introduction to Quantum Physics – Computation with Qubits – Periodicity – Quantum Fourier Transform – Kitaev’s Phase Estimation Algorithm – Search and Quantum Oracle – Quantum Problem- Solving – Quantum Cognition – General Model of a Quantum Computer – Quantum Walk – Adiabatic Computation – Quantum Neural Computation.

Introduction to Business Intelligence – Supervised and Unsupervised Machine Learning Methods – Data Mining Process – Data visualization – Analytical Methods – including Regression – Clustering and Decision Trees – Artificial Neural network and its Business Applications – Model Assessment and Deployment – Text Mining and Analytics in Business – Fundamental architecture for functioning business intelligence systems with the support of data-mining & data-warehousing applications.

Introduction – Using Artificial Intelligence Tools to Enhance Security – machine learning applications in modern cyber security and threat detection, botnet detection – intrusion detection – deep packet inspection – fraud monitoring – malware detection – phishing detection – active authentication – Cyber penetration testing techniques and tools – Politics – Big data and Decision-Making Process – Artificial Intelligence in Politics – Future of AI in Advancing Cyber Security.

Particular emphasis is placed on the importance of practical experience and all teaching involves industry standard hardware, software, methods and techniques. Students asked to complete training on chosen area of specialization to be familiar with the industry.

This course will continue for two semesters. In the first semester; a group of students will select one of the projects proposed by the department and analyze the underlying problem. In the second semester; the design and implementation of the project will be conducted.