DE0478 Artificial Intelligence

Code DE0478
Name Artificial Intelligence
Status Compulsory/Courses of Limited Choice
Level and type Post-graduate Studies, Academic
Field of study Computer Science
Faculty Faculty of Computer Science, Information Technology and Energy
Academic staff Jānis Grundspeņķis
Credit points 6.0
Parts 1
Annotation Artificial intelligence is developing towards four goals – to create systems that think or act like humans, as well as systems that think or act rationally. In this study course students acquire knowledge about a modern approach to artificial intelligence – development of intelligent agents. The study course is focused on properties, environment, architectures and programmes of intelligent agents, logical agents, planning, uncertain knowledge and reasoning, making simple and complex decisions, inductive learning, learning decision trees, neural networks and reinforcement learning. In development of a course work students must use their theoretical knowledge for implementation of agent based intelligent systems and analysis of their performance..
Contents
Content Full- and part-time intramural studies Part time extramural studies
Contact hours Independent work Contact hours Independent work
Definition and properties of intelligent agents. 2 2 0 0
The structure of intelligent agents. 2 2 0 0
Reflex agents and their varieties. 2 2 0 0
Agent environments and their characteristics. 2 2 0 0
Logical agents. 2 2 0 0
Intelligent agents. 4 8 0 0
Searching. 0 8 0 0
Knowledge representation and construction of knowledge base for logical agents. 2 2 0 0
Inference procedures of logical agents. 2 2 0 0
Inference rules in first-order logic. 2 2 0 0
Uncertain knowledge and probabilistic reasoning. 4 4 0 0
Bayesian networks, representing the full joint distribution, conditional independence relations. 2 2 0 0
The basics of utility theory. 2 2 0 0
Utility functions, dominance, preference structure and multiattribute utility. 2 2 0 0
Decision networks and decision-theoretic expert systems. 2 2 0 0
Sequential decision problems. 4 8 0 0
Utilities of states and value iteration algorithm. 2 4 0 0
Policy iteration. 2 4 0 0
Planning. 4 8 0 0
Learning agents and their components. 2 2 0 0
Inductive learning. 4 8 0 0
Learning decision trees. 2 4 0 0
Neural networks and their structures. 2 2 0 0
Learning neural networks. 2 4 0 0
Perceptrons (single-layer feed-forward neural networks) and linearly separable functions. 2 2 0 0
Multilayer feed-forward neural networks and back-propagation process. 2 2 0 0
Principles of reinforcement learning. 4 4 0 0
Total: 64 96 0 0
Goals and objectives
of the course in terms
of competences and skills 		The goal of the study course is to give theoretical knowledge and practical skills for development of agent-based intelligent computer systems. The objectives of the study course are: 1) present the intelligent agent paradigm, agent properties, architectures, structure and behaviour; 2) develop skills to use knowledge representation schemas and methods of knowledge processing; 3) provide knowledge about modelling of decision making and planning agents; 4) develop skills to use machine learning algorithms.
Learning outcomes
and assessment 		Understands properties, architectures, environments and behaviour of intelligent agents. - The first laboratory task or the corresponding individual task. Exam.
Knows structure of logical agents, knowledge representation and inference procedures. - Exam.
Can apply various search algorithms. - The second laboratory task or the corresponding individual task.
Understands structure of planning agents and representation of planning problems using formal languages. - The third laboratory task or the corresponding individual task.
Knows methods for uncertain knowledge processing and can apply modelling methods of decision-making agents. - Exam.
Can apply methods for learning decision trees and neural networks. - The fourth laboratory task or the corresponding individual task.
Can apply algorithms of reinforcement learning. - The fifth laboratory task or the corresponding individual task. Exam.
Evaluation criteria of study results
Course work, including laboratory tasks - 50%
Exam - 50%
 
Course prerequisites Basis strategies of state space search and knowledge representation schemas.
Course planning
Part CP Hours Tests
Lectures Practical Lab. Test Exam Work
1 6.0 48.0 0.0 16.0 *
[Extended course information PDF]