ECTS credits ECTS credits: 3
ECTS Hours Rules/Memories Student's work ECTS: 45 Hours of tutorials: 8 Expository Class: 12 Interactive Classroom: 10 Total: 75
Use languages Spanish, Galician
Type: Ordinary subject Master’s Degree RD 1393/2007 - 822/2021
Center Faculty of Biology
Call: Second Semester
Teaching: With teaching
Enrolment: Enrollable | 1st year (Yes)
It is taught in the Faculty of Informatics of the University of A Coruña
On one hand, Students may be familiar with the most important knowledge representation techniques for intelligent systems. On the other hand, they will study an example of distributed knowledge representation which is founded on a biological system for that knowledge representation
Master Classes
1. HISTORY AND BASICAL CONCEPT OF ADAPTATIVE SYSTEMS
1.1 Historical evolution and previous Works.
1.2 Birth of the technique.
2. MODELS
2.1 Modelization Process
2.2 Comparison between biological element and formal element.
3. NATURAL KNOWLEDGE AND ITS REPRESNTATION
3.1 Principal characteristic of real life knowledge.
3.2 Knowledge Representation methods.
4. REASONING AND LEARNING
4.1 Reasoning methods
4.2 Kinds of Learning.
5. ADAPTATIVE SYSTEMS METHODOLOGY
5.1 Introduction.
5.2 Methodology steps.
6. BASIC APPLICATIONS OFCONECTIONIST SYSTEMS
6.1 Previously consideration for application
6.2 Applications.
PRACTICES
- Analysis and Creativity Practices in teamwork groups
- Discussion Practices.
- Computer Laboratory Practices
SEMINARS
The last tends and novel results of recent scientific works will be exposed to the students.
•Arbib M.A.: "Cerebros, Máquinas y Matemáticas". Ed. Alianza Universidad. Madrid. 1987.
•Arbib, M.A.: “The handbook of brain theory and neural networks”. Cambridge, Massachusetts. MIT Press. 1995.
•Grossberg, S.: "Neural Networks and Natural Inteligence". Editor: MIT Press, 1988.
•Hertz, J., Krogh, A. & Palmer, R.: "Introduction to the Theory of Neural Computation". Santa Fe Institute, Addison-Wesley Editores 1991.
•Hinton, G.E.: “How Neural Networks Learn from Experience”. Scientific American, 267, 144-151. 1992.
•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.
•McCulloch, W.S., Arbib, M.A. & Cowan, J.D. "Neurological Models and Integrative Processes". In Yacovits, Jacobi and Goldstein. Ed. Selft-Organizing Systems.Spartan bocks. Washington. 1969.
•Minsky, M. & Papert, S.: "Perceptrons". Cambridge, MIT Press. 1988.
•Ramón y Cajal, S.: "Textura del Sistema Nervioso del Hombre y los Vertebrados". tomo I. Ed. Alianza. 1989.
•Rosenblueth, A., Wiener, N, and Bigelow, J.: "Behavior, Purpose and Teleology". Phylosophy of Science nº10, pp. 18-24. 1943.
•Rumelhart, D.E., Widrow, B. & Lehr, M. A.: "The basic ideas in neural networks". Comm. ACM. Num 37. pp 87-92. 1994.
Understanding the neurobiological base of Adaptative Systems, this is responsible of the structure and functionalities of these systems.
Be familiar with Natural knowledge and its representations
Understand the reasoning methods of Adaptative Systems and Know the different learning methods for these ones
Learn how to model an Adaptative System
Train and Construct Adaptative Systems by following a formal methodology
Master Classes
Interactive Classes: Seminars and practices
Individual or Small Groups Tutorships
Evaluation Activities
- Interaction at presential classes
- Preparation and Presentation of a tutorized work about this material topics
- Theory and practice writing exam
Master Classes : 10 hours
Interactive Classes: Seminars and practices: 10 hours
Individual or Small Groups Tutorships: 8 hours
Evaluation Activities : 2 hours
Individual Learning: 20 hours
Preparation of practices or papers: 25 hours
It could be interesting for the students to take this material at the same time with the one entitle Computational Neuroscience, Development and Evolution of the Nervous System