| TOPICS |
| 1. Mathematical and theoretical methods in computational intelligence. |
1.1 Complex and social systems.
1.2 Evolutionary and genetic algorithms.
1.3 Fuzzy logic.
1.4 Mathematics for neural networks.
1.5 RBF structures.
1.6 Self-organizing networks and methods.
1.7 Support vector machines. |
| 2. Neurocomputational formulations |
2.1 Single-neuron modelling.
2.2 Perceptual modelling.
2.3 System-level neural modelling.
2.4 Spiking neurons.
2.5 Models of biological learning |
| 3. Learning and adaptation |
3.1 Adaptive systems.
3.2 Imitation learning.
3.3 Reconfigurable systems.
3.4 Supervised, non-supervised, reinforcement and statistical algorithms. |
| 4. Emulation of cognitive functions |
4.1 Decision Making.
4.2 Multi-agent systems.
4.3 Sensor mesh.
4.4 Natural language.
4.5 Pattern recognition.
4.6 Perceptual and motor function (visual, auditory, tactile, virtual reality, etc.).
4.7 Robotics.
4.8 Planning motor control.
|
| 5. Bio-inspired systems and neuro-engineering |
5.1 Embedded intelligent systems.
5.2 Evolvable computing
5.3 Evolving hardware.
5.4 Microelectronics for neural, fuzzy and bioinspired systems
5.5 Neural prostheses,
5.6 Retinomorphic systems
5.7 Brain-computer interfaces (BCI)
5.8 Nanosystems
5.9 Nanocognitive systems |
| 6. Ambient intelligence |
6.1 Unobtrusive hardware
6.2 Seamless mobile/fixed communication and computing infrastructure
6.3 Dynamic and massively distributed device networks.
6.4 Human-centric computer interfaces
6.5 Dependable and secure systems and devices
6.6 Ambient assisting living (AAL) |
| 7. Applications |
7.1 Adaptive interfaces.
7.2 Biomimetic applications
7.3 Data analysis and pre-processing
7.4 Data mining
7.5 Economy and financial engineering.
7.6 Fuzzy systems for control.
7.7 Internet
7.8 Neural networks for control.
7.9 Power systems.
7.10 Signal processing
7.11 Telecommunication applications.
7.12 Time series and prediction |