• Mathematical and theoretical methods in computational intelligence:

    Mathematics for neural networks. RBF structures. Self-organizing networks and methods. Support vector machines and kernel methods.  Fuzzy logic. Evolutionary and genetic algorithms.
  • Neurocomputational formulations:

    Single-neuron modelling.  Perceptual modelling. System-level neural modelling. Spiking neurons. Models of biological learning.
  • Learning and adaptation.

    Adaptive systems. Imitation learning. Reconfigurable systems. Supervised, non-supervised, reinforcement and statistical algorithms.
  • Emulation of cognitive functions.

    Decision Making.  Multi-agent systems. Sensor mesh. Natural language. Pattern recognition. Perceptual and motor functions (visual, auditory, tactile, virtual reality, etc.). Robotics. Planning motor control.
  • Bio-inspired systems and neuro-engineering.

    Embedded intelligent systems. Evolvable computing.  Evolving hardware. Microelectronics for neural, fuzzy and bioinspired systems. Neural prostheses. Retinomorphic systems. Brain-computer interfaces (BCI) Nanosystems. Nanocognitive systems.
  • Hybrid Intelligent Systems.

    Soft Computing. Neuro-fuzzy systems. Neuro-evolutionary systems.  Neuro-swarm. Hybridizatiion with novel computing paradigms: Qantum computing, DNA computing, membrane computing. Neural dynamic logic and other methods; etc.
  • Applications.

    Image and Signal Processing. Ambient intelligence. Biomimetic applications. System identification, process control, and manufacturing. Computational Biology and Bioinformatics.  Internet Modeling, Communication and Networking. Intelligent Systems in Education.  Human-Robot Interaction. Multi-Agent Systems. Time series analysis and prediction. Data mining and knowledge discovery.


Diseño: dixi;    Contenidos: Alberto Prieto;    Programación: Beatriz Prieto;     ¡CSS Válido!     Valid XHTML 1.0 Strict Taw3 Valid