Checking date: 23/04/2019


Course: 2019/2020

Intelligent systems design
(14347)
Study: Master in Computer Engineering (228)
EPI


Coordinating teacher: FERNANDEZ ARREGUI, SUSANA

Department assigned to the subject: Department of Computer Science and Engineering

Type: Compulsory
ECTS Credits: 6.0 ECTS

Course:
Semester:




Students are expected to have completed
None
Competences and skills that will be acquired and learning results.
* Specific competences: CE12. Ability to apply mathematical, statistical, and artificial intelligence methods to model, design, and develop applications, services, intelligent systems and knowledge-based systems. CG1. Ability to project, compute and design products, processes and installations in all areas of Computer Science CG8. Ability to apply acquired knowledge and solve problems in new environments or less known in wider and multidisciplinary contexts, being able to integrate those concepts. * Learning results: o Ability to design an intelligent system, selecting the most appropriate architecture. (RA1, RA2, RA3, RA5, RA6) o Ability to integrate computational sensing and actuation capabilities in a computer system. (RA1, RA2, RA3, RA5, RA6) o Ability to select the most adequate knowledge representation formalism to model an intelligent system. (RA1, RA2, RA3, RA5, RA6) o Ability to develop computer systems that integrate reasoning, planning, search, control and learning techniques. (RA1, RA2, RA3, RA5, RA6) o Know mathematical, statistical, and artificial intelligence methods that are used in the design and development of intelligent systems. (RA1, RA2, RA3, RA5, RA6) o Ability to design and develop intelligent systems to make decisions to solve problems under uncertainty (RA1, RA2, RA3, RA5, RA6)
Description of contents: programme
1. Intelligent systems 1.1 Design of intelligent systems 1.2 Cognitive and execution architectures 1.3 Case studies 2. Interaction with the environment 2.1 Computational perception 2.2 Case studies 3. Knowledge representation 3.1 Knowledge representation paradigms 3.2 Modeling of intelligent systems 3.3 Case studies 4. Reasoning 4.1 Heuristic Search 4.2 Planning 4.3 Other reasoning mechanisms 4.4 Case studies 5. Machine learning 5.1 Supervised techniques 5.2 Unsupervised techniques 5.3 Case studies
Learning activities and methodology
* Theory classes o Focus on acquiring the specific competences, by presenting the topics the students should acquire. Students will be given slides and they will have a list of basic reference books that will allow them to complete those subjects in which they are more interested. The focus will be on general aspects of the application of Artificial Intelligence techniques to the development of computational systems, including decision support systems. * Case-based classes. o Students will solve practical cases related to knowledge representation, design of intelligent systems based on reasoning, planning, search, control and learning. * Homeworks. o They will be preferably done in groups and they will be tailored towards the design and development of intelligent systems. We will consider systems that integrate several artificial intelligence techniques to solve real-world problems. Also, those techniques will be applied to decision making. * Personal work of students. o Focused towards the acquisition of the ability of auto-organization and planning of individual work and learning process
Assessment System
  • % end-of-term-examination 50
  • % of continuous assessment (assigments, laboratory, practicals...) 50
Basic Bibliography
  • E. Rich and K. Knight. Artificial Intelligence. McGraw Hill. 1991
  • S. Russell and P. Norvig. Artificial Intelligence: A modern approach. Pearson Education. 2014

The course syllabus and the academic weekly planning may change due academic events or other reasons.