The aim of this course is to present to the students, different advanced techniques in computational intelligence. Once acquired the basic knowledge of fuzzy, evolutionary and neural computation in the CI-MAI course, the students are ready to go through other powerful computational intelligence approaches such as hybrid techniques: neuro-fuzzy and genetic-fuzzy systems, fuzzy inductive reasoning, fuzzy and heterogeneous neural networks, as well as recurrent neural networks and incremental methods for neural networks construction.
Person in charge
René Alquezar Mancho (
Enrique Romero Merino (
Luis Antonio Belanche Muñoz (
Maria Angela Nebot Castells (
Generic Technical Competences
CG3 - Capacity for modeling, calculation, simulation, development and implementation in technology and company engineering centers, particularly in research, development and innovation in all areas related to Artificial Intelligence.
CG4 - Capacity for general management, technical management and research projects management, development and innovation in companies and technology centers in the area of Artificial Intelligence.
Technical Competences of each Specialization
CEA11 - Capability to understand the advanced techniques of Computational Intelligence, and to know how to design, implement and apply these techniques in the development of intelligent applications, services or systems.
CEP2 - Capability to solve the decision making problems from different organizations, integrating intelligent tools.
CEP3 - Capacity for applying Artificial Intelligence techniques in technological and industrial environments to improve quality and productivity.
CT3 - Ability to work as a member of an interdisciplinary team, as a normal member or performing direction tasks, in order to develop projects with pragmatism and sense of responsibility, making commitments taking into account the available resources.
To understand the fuzzy inductive reasoning methodology for modelling systems and predicting their behavior.
To apply the fuzzy inductive reasoning methodology to the simulation of environmental, biomedical, industrial or economical processes.
To understand the different ways of designing computational intelligence hybrid techniques by integrating
fuzzy logic, neural networks and evolutionary algorithms.
To apply computational intelligence hybrid techniques to solve complex data mining problems in real scenarios.
To understand some of the most advanced and recent techniques in the field of neural networks (e.g. recurrent neural nets, extreme learning machines, deep neural nets).
To apply neural network advanced techniques to solve complex data mining problems in real scenarios.
Fuzzy inductive reasoning
The fuzzy inductive reasoning (FIR) methodology allows the qualitative modelling of systems and the quantitative prediction of their behavior.
Hybrid fuzzy systems: neuro-fuzzy systems and genetic-fuzzy systems
The hybrid fuzzy systems improve the abilities of fuzzy systems by introducing neural networks and genetic algorithms to learn and adapt their parameters for a better performance.
Fuzzy and heterogeneous neural networks
Similarity-based neural networks, possibly trained using evolutionary algorithms, allow the processing of fuzzy and heterogeneous data in classification or regression problems without the need of data coding.
Incremental methods for neural network construction and extreme learning machines
Incremental methods for neural network construction allow an efficient computation of simple models with good generalization performance. Extreme learning machines do so by assigning random weights to some part of the neural architecture and optimizing the rest of weights.
Deep neural networks
Deep neural networks ,,,, (to complete)
Recurrent neural networks
Discrete-time recurrent neural networks allow the learning and processing of dynamic input/output tasks such as time-series prediction, sequence classification and translation.
Fuzzy Inductive Reasoning
Development of the corresponding topic and laboratory exercises Objectives:12 Contents:
15 (Outside class hours) Type:
Theory classes will introduce the knowledge, techniques and concepts required to apply them
in practice during the laboratory classes. Theory classes will be mainly of the type magisterial
lecture, but some of them may be of the type exposition-participation, with the participation of
the students in solving problems or exercises.
Laboratory classes have as objective that the students work with software tools which allow the
application to real problems of the techniques presented in theory classes. Students will use
these tools to develop their practical work of the course, which will consist of a part of autonomous
individual work and a part of cooperative work in a team of 2/3 people. Some time of the laboratory
classes will be devoted to the orientation and supervision by the professor of these autonomous
and cooperative works.
A final exam will evaluate the specific objectives of understanding the concepts and methods
presented during the course. On the other hand, the individual and cooperative practical works
by the students will allow the evaluation of the specific objectives of applying the presented
techniques, as well as the general, basic and transverse skills associated with the course.
The technical skills mark (M) is calculated as follows:
M = 0.40*FINAL_EXAM + 0.60*PRACT_WORK
* FINAL_EXAM refers to the mark of the final exam;
* PRACT_WORK refers to the global mark of the practical works (at least 3 works) defined by the teachers during the course and carried out in small groups; it is calculated as the average of the marks of these practical works.
Nevertheless, M will be NP if the student do no present anything in the assessment activities.
The generic skill (Teamwork) mark will be directly given by PRACT_WORK.
Fuzzy inductive reasoning for variable selection analysis and modelling of biological systems -
NEBOT, Àngela; CELLIER, François E; CARVAJAL, Raúl; MUGICA, Francisco,
International Journal of General Systems, 2009 / Volume 38, Issue 8, pages 793-811. ISBN: 0308-1079
A fast learning algorithm for deep belief nets -
HINTON, G. E; OSINDERO, S.; and TEH, Y. W. ,
Neural Computation, 2006 / Vol. 18, pp:1527-1554. ISBN: 0899-7667
Reducing the dimensionality of data with neural networks -
HINTON, G. E. and SALAKHUTDINOV, R. R. ,
Science, 2006 / Vol. 313, pp:504-507. ISBN: 0036-8075
Confidence measures for predictions in fuzzy inductive reasoning -
CELLIER, François E; LÓPEZ, Josefina; NEBOT, Àngela; CEMBRANO, Gabriela, International Journal of General Systems ,
2010 / Vol.39 (8), pp: 839-853.
Optimization of fuzzy partitions for inductive reasoning using genetic algorithms -
ACOSTA, Jesús.; NEBOT, Àngela; VILLAR, Pedro; and FUERTES, Josep Maria, International Journal of Systems Science ,
2007 / Vol. 38, No. 12, pp: 9911011.
Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence -
JANG, Jyh-Shing Roger; SUN, Chuen-Tsai; MIZUTANI, Eiji , Prentice Hall ,