SALEIE logo that when clicked will open a new window to access the SALEIE home page.

Strategic ALignment of Electrical and Information Engineering in European Higher Education Institutions

European Union flag.



User guide



Click on the image to the left to select the project website section to go to.

Click on the images to the left and above to select the project website section to go to (Technical Challenge Areas, Student and Staff Support Hub or Governance) OR select the Student and Staff Support Hub below.

Technical Global Challenges Areas Student and Staff Support HUB Higher Education Policy Hub


Higher Education Technical Challenges Hub: Module Specification

ICT17M2 Artificial Intelligence and Machine Learning

pdf version of module specification

Download the module specification

pdf version of module specification








Module name:

Artificial Intelligence and Machine Learning

Scope and form:

face to face

Duration (weeks; Hours/week):

15 weeks, 4h/week (180 hours of workload)

Type of assessment:

During the semester students must solve a project for which they can obtain a maximum of 30 points, and a test to obtain a maximum of 10 points. From the project, as well as from the test they must obtain at least half. The project is presented orally in a group. To grant the credits it is necessary to get at least 21 points. The maximum number of points students can obtain during the semester is 40 points. The final exam consists of three modules: an example, a test and a theoretical module. For each module, students can obtain maximally 20 points, 60 points in total.  Students must obtain at least 10 points in each module. The resulting assessment is then calculated based on the ECTS credit system.

Qualified Prerequisites:


General module objectives:

The objective of the module are as follows: to introduce the basics of artificial intelligence, the concept of intelligent agents, to analyze problem solving and search techniques, to understand how to represent knowledge, to do planning, to reason with uncertain knowledge, to analyze techniques for decision making, and finally to introduce neural networks.

Topics and short description:

Overview: foundations, scope, problems, and approaches of AI.
Intelligent agents: reactive, deliberative, goal-driven, utility-driven, and learning agents
Problem-solving through Search: forward and backward chaining, state-space search, blind search, heuristic search, problem-reduction; A, A*, AO* algorithms, game playing, minimax search, constraint propagation, neural networks, stochastic processes, and evolutionary search algorithms, sample applications.
Knowledge Representation and Reasoning: ontologies, foundations of knowledge representation and reasoning, representing and reasoning about objects, relations, events, actions, time, and space; predicate logic, situation calculus, description logics, reasoning with defaults, reasoning about knowledge, sample applications.
Planning: planning as search, partial order planning, construction and use of planning graphs
Representing and Reasoning with Uncertain Knowledge: probability, connection to logic, independence, Bayes rule, Bayesian networks, probabilistic inference, sample applications.
Decision-Making: basics of utility theory, decision theory, sequential decision problems, elementary game theory, sample applications.
Machine Learning and Knowledge Acquisition: learning theory, supervised learning, unsupervised learning, reinforcement learning.
Neural networks: pattern recognition, multilayer neural networks, self-organizing neural networks, sample applications.

Learning outcomes:




Fundamentals for problem representation and reasoning

Able to represent problems and to formally reason about them

Students must understand how to represent problems and to reason about them

Understanding how to use efficient search techniques

Able to do practical application of search techniques

Students must be able to use efficient methods for searching

Fundamentals for using modern planning techniques

Being able to use planning techniques

Students must be able to apply planning techniques for problem solving

How to design, to develop and to manage systems with uncertain knowledge representation

Be able to manage systems with uncertain knowledge representation

Students must have the capability to manage uncertain knowledge representation techniques

Understanding the basics of decision-making techniques

Capability to understand and to use decision making techniques

Students must be able to understand decision-making techniques for problem solving

Fundamentals different machine learning techniques for knowledge acquisition

Capability to analyze and evaluate the best options for using every machine learning technique depending on the context.

Students must understand the basics of Machine Learning and be able to design and implement systems to take advantage of it

Understand the differences and the application of the different neural network models

Capability to understand and to select the right neural network for practical applications

Students must discriminate among the different neural network models for different applications

Recommended literature:

Main reference:
Russell and Norvig. Artificial Intelligence: A Modern Approach. 3rd Edition. A comprehensive reference for all the AI topics of the module.
  Complementary references: Woolridge, M. Introduction to MultiAgent Systems. New York: Wiley (2002).
Introduction to Machine Learning (3rd edition). Ethem Alpaydin, MIT Press (2014) ISBN-13: 978-0262028189.
Tom Mitchell, Machine Learning. Avalilable at:
Bishop, C. M. Neural Networks for Pattern Recognition. New York: Oxford University Press (1995).
Cowell, R. G. Lauritzen, S. L., and Spiegelhalter, D. J. Probabilistic Networks and Expert Systems Berlin: Springer (2005).
MacKay, David. Information Theory, Inference, and Learning Algorithms. Cambridge, UK: Cambridge University Press, 2003. ISBN: 9780521642989. Available at:
Bather, J. Decision Theory: An Introduction to Dynamic Programming and Sequential Decisions. New York: Wiley (2000).
Ghallab, M., Nau, D., & Traverso, P. Automated Planning : Theory & Practice. Palo Alto: Morgan Kaufmann (2005). Available free online.
Hastie, Tibshirani, and Friedman. The elements of statistical learning. Available free online.
Sutton and Barto. Reinforcement Learning: An Introduction.
Tsang. Foundations of constraint satisfaction. Available free online.