| Study programme competencies |
| Code | Study programme competences |
| A21 | Coñecemento e aplicación dos principios fundamentais e técnicas básicas dos sistemas intelixentes e a súa aplicación práctica. |
| B1 | Capacidade de resolución de problemas |
| B3 | Capacidade de análise e síntese |
| B5 | Habilidades de xestión da información |
| B9 | Capacidade para xerar novas ideas (creatividade) |
| C6 | Valorar criticamente o coñecemento, a tecnoloxía e a información dispoñible para resolver os problemas cos que deben enfrontarse. |
| C8 | Valorar a importancia que ten a investigación, a innovación e o desenvolvemento tecnolóxico no avance socioeconómico e cultural da sociedade. |
| Learning aims | |||
| Learning outcomes | Study programme competences | ||
| Conocimiento y aplicación de los principios fundamentales y técnicas básicas de los sistemas inteligentes y su aplicación práctica. | A21 |
B1 B3 B5 B9 |
C6 C8 |
| Contents |
| Topic | Sub-topic |
| 1. Introduction | 1.1. An historical perspective 1.2. Preliminary aspects 1.3. General considerations |
| 2. Problem-Solving | 2.1. Introduction to solving problems in AI 2.2. The state space concept. Searching 2.3. General characteristics of searching processes 2.4. Uninformed search strategies 2.5. Informed search strategies. Heuristic functions 2.6. Local search |
| 3. Structured Knowledge Representation | 3.1. Introduction 3.2. Declarative methods 3.3. Procedural methods 3.4. Examples and a practical case |
| 4. Production Systems | 4.1 Architecture: Knowledge base, active memory, inference engine 4.2. Dynamics of rule production systems 4.3. Basic cycle of a production system |
| 5. A Brief Introduction to Reasoning in AI | 5.1. Introduction 5.2. Categorical model 5.3. Bayesian reasoning fundamentals |
| 6. Connectionist Systems: Origin and Context; Biological Fundamentals | 6.1 Historical Evolution and Precursors. 6.2 Birth of Connectionist Systems. 6.3. Biological Basis of the Adaptive Systems 6.4. Adquisition and organization of the knowledge in Adaptive Systems. |
| 7. Architecture, Feeding and Learning in Connectionist Systems | 7.1 Processing element in Connectionist Systems. 7.2 Comparison between the biological element and the formal one. 7.3 Feeding and architecture of the Connectionist Systems. 7.4 Learning in Connectionist Systems. |
| 8. Feed-Forward Connectionist Systems | 8.1. Adaline 8.2. Perceptron 8.3. Aplications |
| 9. Other Models of Connectionist Systems | 9.1 Self-organizing networks 9.2. Other self-organizing models: Growing neural networks 9.3. Hopfield network. |
| 10. New approaches in Sub-Symbolic Artificial Inteligence | 10.1 Evolutionary Computation. 10.2 Artificial Life. 10.3 NBIC Technologies. |
| Planning | ||||
| Methodologies / tests | Competencies | Ordinary class hours | Student’s personal work hours | Total hours |
| Laboratory practice | A21 B1 B5 | 20 | 0 | 20 |
| Supervised projects | B3 B9 | 10 | 20 | 30 |
| Guest lecture / keynote speech | C6 C8 | 30 | 60 | 90 |
| Personalized attention | 10 | 0 | 10 | |
| (*)The information in the planning table is for guidance only and does not take into account the heterogeneity of the students. | ||||
| Methodologies |
| Methodologies | Description |
| Laboratory practice | - Using Symbolic Artificial Intelligence techniques to solve problems. - Using Subsymbolic Artificial Intelligence techniques to solve problems. |
| Supervised projects | - Study of the different models of symbolic intelligent systems and identification of the concepts involved in these models in practical application examples. - Search, analysis of real problems that show the application of Sub-symbolic Intelligence Artificial Systems. |
| Guest lecture / keynote speech | Imparting of the contents of the different topics of the subject, encouraging the participation of students in the understanding of practical examples. |
| Personalized attention |
|
|
| Assessment | |||
| Methodologies | Competencies | Description | Qualification |
| Guest lecture / keynote speech | C6 C8 | Written exam to assess knowledge of the matter. |
60 |
| Laboratory practice | A21 B1 B5 | - Only work submitted before deadline of students who have attended the hours assigned to the practices are scored. | 30 |
| Supervised projects | B3 B9 | - Only work submitted before deadline of students who have attended the hours assigned to the TGR are scored. | 10 |
| Assessment comments | |||
|
In order to pass the subject will be required to pass the exam of theory and also achieve at least 5 points after adding the note of written exam, with the notes of practice and TGR. |
|||
| Sources of information |
| Basic |
Moret et al. (2005). Fundamentos de inteligencia artificial. Servicio de publicaciones de la UDC (2ª ed, 2ª imp)
José T. Palma, Roque Marín Morales et al. (2008). Inteligencia artificial - Técnicas, métodos y aplicaciones. McGraw Hill (1ª ed.)
Russell & Norvig (2004). Inteligencia artificial: un enfoque moderno. Pearson (2ª ed) |
|
TEMAS 6 y 7 Cajal, S.: “Textura del SistemaNervioso del Hombre y los Vertebrados”. Tomo I. Ed. Alianza. 1989. Haykin, S.: “Neural Networks: A Comprehensive Foundation”. McMillan College Publishing. New York. 1994. Hertz, J., Krogh, A. & Palmer, R.: “Introduction to the Theory of Neural Computation”. Santa Fe Institute, Addison-Wesley Editores 1991. McCulloch, W. S., and Pitts, W.: “A Logical Calculus of the Ideas Inmanent in the Neural Nets”. Buletin of Mathematical Biophysics, vol. 5, pp. 115-137. 1943. Minsky,M. & Papert, S.: “Perceptrons”. Cambridge,MIT Press, 1969. Rosenblueth, A., Wiener, N, and Bigelow, J.: “Behavior, Purpose and Teleology”. Phylosophy of Science nº10, pp. 18-24. 1943. Wiener, N.: “Cibernetics or Control and Communications in the Animals and Machines”. Ed. MIT. Press. 1948. TEMAS 8 y 9 Hertz,J., Krogh, A. & Palmer, R.: “Introduction to the Theory of NeuralComputation”. Santa Fe Institute, Addison-Wesley Editores 1991. Hopfield, J. & Tank, D.: “Computing with Neural Circuits” A Model”. Science, vol. 233, pp. 625-633. 1986. Kohonen, T.: “Self organizing maps”. Springer Velag. Berlín. Segunda Edición. 1995. Ríos, J.Pazos, A. y otros: “Estructura, Dinámica y Aplicaciones a las Redes NeuronasArtificiales”. Ed. Ceura. Madrid.1991. TEMA 10 Gestal M, Rivero D et al. Introducción a los Algoritmos Genéticos y la Programación Genética. Servicio de Publicacións da UDC. 2010. Yao, X. “Evolving Artificial Neural Networks”. In:Proc. IEEE, Vol. 87 nº9 1423-1447. 1999. |
|
| Complementary | |
|
|
| Recommendations | ||||
| Subjects that it is recommended to have taken before | ||||
|
| Subjects that are recommended to be taken simultaneously |
| Subjects that continue the syllabus | ||||
|
| Other comments | |