Intelligent Systems


Intelligent Agents (Sem. 1)

Learning outcomes

- Understand the general notions of agent and multiagent systems, naming and classifying different properties
of agents and environments;
- Build agents with a given architecture;
- Design a society of agents and use it in the solution of a problem;
- Develop solutions, in many applications areas, using an agent-based methodology for problem solving;
- Build a society of agents that comunnicate using an agent-based language and using different platforms.

Syllabus

Introduction
Intelligent Agents
Multiagent Systems
Coordination
Argumentative Systems
Applications of Intelligent Agents
Security, Trust and Legal Relations

Teaching methodologies and evaluation

Individualized teaching: guided study; assignment teaching; teaching per module.
Socialized teaching: small groups discussion; guided discussion; brainstorming; lecture.
Social and individualized teaching: project; problems; search.
Mandatory contact sessions.
This curricular unit (CU) is built up from several assessment instruments: practical assignments, both
individual and in group, and theoretical/written exams.
The final CU grade will result from a weighted average of all assessment instruments used.

Bibliography

Wooldrige M., An Introduction to Multiagent Systems, John Wiley & Sons, ISBN 0 47149691X, 2002;
d'Inverno M., Luck M., Understanding Agent Systems, Springer, ISBN: 978-3540407003, 2003;
Bellifemine F., Caire G., Greenwood D., Developing Multi-Agent Systems with JADE, John Wiley & Sons, ISBN:
978-0470057476, 2007;

Learning and Knowledge Extraction (Sem. 1)

Learning outcomes

- Identify, describe and define the basic concepts regarding data systems, analytical processing, data mining,
knowledge extraction and machine learning.
- Use, classify and assess existing or to develop applications and frameworks.
- Select the adequate methodologies and use software and frameworks to solve real world problems, to data
analysis, data mining, knowledge extraction and decision making.
- To know and to be able to implement the main algorithms related to data mining techniques, knowledge
extraction and autonomous learning.

Syllabus

Machine Learning Systems
- Artificial Neural Networks
- Genetic Algorithms and Genetic Computation
- Particle Swarm
- Case Based Reasoning
Knowledge Extraction
- Basic Cooncepts
- Objectives
- Methodologies
- Techniques
- Tools
Applications and Frameworks

Teaching methodologies and evaluation

Individualized teaching: guided study; assignment teaching; teaching per module.
Socialized teaching: small groups discussion; guided discussion; brainstorming; lecture.
Social and individualized teaching: project; problems; search.
Mandatory contact sessions.
This curricular unit (CU) is built up from several assessment instruments: practical assignments, both
individual and in group, and theoretical/written exams.
The final CU grade will result from a weighted average of all assessment instruments used.

Bibliography

Han J., Kamber M., "Data Mining: Concepts and Techniques", Morgan Kaufmann, 2001;
Haykin S., "Neural Networks: A Comprehensive Foundation", 2nd Edition, Prentice-Hall, New Jersey, 1999;
Goldberg D., "Genetic Algorithms in Search, Optimization, and Machine Learning", Addison Wesley, 1989.

Natural Computing (Sem. 2)

Learning outcomes

- Identify, describe and define the basic concepts regarding Evolutionary Computation (e.g., Virtual Minds),
Collective Intelligence (e.g., Particle Swarm) and Soft Computing (e.g., Artificial Neural Networks, Genetic and
Evolutionary Programming).
- Select the best methodologies to problem solving, as well as the best computational paradigms that fit best to
problem solving.

Syllabus

Virtual Minds
Artificial Neural Networks
Genetic Algorithms
Genetic Programming
Evolutionary Strategies
Evolutionary Programming
Artificial Life Systems
Particle Swarm

Teaching methodologies and evaluation

Individualized teaching: guided study; assignment teaching; teaching per module.
Socialized teaching: small groups discussion; guided discussion; brainstorming; lecture.
Social and individualized teaching: project; problems; search.
Mandatory contact sessions.
This curricular unit (CU) is built up from several assessment instruments: practical assignments, both
individual and in group, and theoretical/written exams.
The final CU grade will result from a weighted average of all assessment instruments used.

Bibliography

De Jong K., Evolutionary Computation: A Unified Approach, MIT Press, 2006;
Eiben A.E. , Smith J.E., Introduction to Evolutionary Computing, Springer-Verlag, New York, 2003;
Engelbrecht A., Computational Intelligence: An Introduction, Wiley & Sons. ISBN 0-470-84870-7, 2007.

Autonomous Systems (Sem. 2)

Learning outcomes

- Identify, describe and define the basic concepts regarding Autonomous Systems and Robotic Agents.
- Build Autonomous Systems making use of the notion of Intelligent Agents.
- Know and be able to use knowledge gathered from sensors.
- Know and be able to use the actuators enabling mobility and navigation.
- Study and develop coordination methods and interaction with the environment.
- Use simulation and complexity analysis to apply to problem solving.

Syllabus

Autonomous Robotic Systems
Control Architectures for Autonomous Systems
Sensors and Actuators
Perception, Mobility and Navigation
Multiagent Robotic Systems
Coordination and Interaction
Autonomous Systems Applications and Frameworks
Simulation

Teaching methodologies and evaluation

Individualized teaching: guided study; assignment teaching; teaching per module.
Socialized teaching: small groups discussion; guided discussion; brainstorming; lecture.
Social and individualized teaching: project; problems; search.
Mandatory contact sessions.
This curricular unit (CU) is built up from several assessment instruments: practical assignments, both
individual and in group, and theoretical/written exams.
The final CU grade will result from a weighted average of all assessment instruments used.

Bibliography

Arkin R., "Behavior Based Robotics", The MIT Press, 1998;
LaValle S., "Planning Algorithms", Cambridge University Press, 2006;
Mitchell H.B., “Multi-Sensor Data Fusion: An Introduction”, Springer, 2007.