| Date | Lecturer | Contents | Materials |
1 | 22.2. | Drchal | Artificial Neural Networks – history, typical problems solved by ANNs, learning algorithms, perceptron | a4m33bia-02ann_intro-2016.pdf Mathematica notebook |
2 | 29.2. | Drchal | MultiLayer perceptron (MLP), Radial Basis Function (RBF) & Group Method of Data Handling (GMDH) | a4m33bia-02mlp_rbf_gmdh-2016.pdf |
3 | 7.3. | Drchal | Backpropagation in detail & Deep Neural Networks (DNNs) | a4m33bia-03backprop-2016.pdf |
4 | 14.3. | Kubalík | Standard genetic algorithm – evolutionary cycle, genetic operators, schema theorem | a4m33bia_sga_2016.pdf |
5 | 21.3. | Kubalík | Genetic programming – basic principles, applications | a4m33bia_geneticprogramming_2015.pdf |
6 | 28.3. | | Easter | |
7 | 4.4. | Drchal | Time series processing, Recurrent Neural Networks (RNN), Jordan/Elman network, BPTT, RTRL, Echo State Networks, LSTM | a4m33bia-06recurrent-2016.pdf |
8 | 11.4. | Drchal | Unsupervised learning, Self-Organizing Map (SOM) | a4m33bia-04som-2016.pdf |
9 | 18.4. | Kubalík | Multiobjective optimization – dominance, Pareto-optimal solutions, NSGA-II, SPEA2 | a4m33bia_moea_2015.pdf |
10 | 25.4. | Kubalík | Evolutionary algorithms with real representation – Evolution strategy, crossover operators, differential evolution | a4m33bia_realcodedea_2016.pdf |
11 | 2.5. | Kubalík | Evolutionary algorithms for dynamic optimization | a4m33bia_eafordynamicoptimization_2015.pdf |
12 | 9.5. | Kubalík | Ant colony optimization, Particle swarm optimization | a4m33bia_aco_pso_2016.pdf |
13 | 16.5. | Drchal | Neuroevolution. NEAT. Direct and indirect encoding of neural networks. Cellular Encoding and HyperNEAT | a4m33bia-13neuroevolution-2016.pdf a4m33bia-13indirect-2016.pdf |
14 | 23.5. | Kubalík / Drchal | Reserve | |