1. Introduction to artificial neural networks (NN): inspiration from biology, basic concepts, NN with logic neurons.

2. Binary / continuous perceptron: supervised learning, error functions, learning rules, continuous function gradient, classification.

3. Linear NN: Vector spaces, autoasociative memory. 4

. Multilayer perceptron: supervised learning, errro backpropagation algorithm, model validation, generalization, model selection.

5. Gradient learning methods, introduction to deep learning.

6. Hebbian unsupervised learning, principle component analysis.

7. Semi supervised learning, self-organizing maps, clustering, topographic view.

8. NN with radial base functions (RBF), model training.

9. Hopfield NN model: deterministic dynamics, attractors, autoasociative memory.

10. Sequence data modeling: forward delayed NN, partial and fully recurrent models (RNN), gradient training algorithms.

11. Organization of Status Space in RNN. Networks with echo states (ESN). 12. Stochastic recurrent NN models: Boltzmann machine, DBN model.

Type of methodology: Combination of lecture and hands-on

Participants receive the certificate of attendance: Yes

Paid training activity for participants: Yes, for all

Participants prerequisite knowledge: Numerical methods (linear algebra, statistics) Domain-specific background knowledge