Learning Outcomes
Cognitive: Foundation and mathematical formalization of the learning and generalization concept and its importance in the computational intelligence field. Comparative conception of the basic neural network and deep learning types. Training principles and learning abilities of the learning machines. Exposition to the diverse applications of neural networks in the fields of pattern recognition, function approximation, data mining and information retrieval.
Skills: Promoting analytic and implementation skills in classification and function approximation using neural networks and deep learning. Implementation of the corresponding neural network training algorithms. Use of deep learning libraries like pytorch or tensorflow for real problems. Promoting programming skills. Ability to complete a learning problem by implementing a neural network algorithm, running experiments on real data, writing a short paper and presenting the results.
Course Content (Syllabus)
Introduction to artificial Neural Networks (ANN). Learning procedures and prototypes. Applications of ANN. Knowledge representation in ANN. Training of Perceptron. The ADALINE algorithm. Multilayer perceptrons (MLPs) and the back-propagation algorithm. Deep Learning. Support vector machines (SVMs). Radial Basis Functions (RBFs). Hebbian learning. Principal Component Analysis Neural Networks (PCA-NN). Non-linear Hebbian models. Independent Component Analysis Neural Networks (ICA-NN). Learning theory and generalization. Applications of ANN to pattern recognition, function approximation, image compression and signal deconvolution.
Course Bibliography (Eudoxus)
1. ΜΗΧΑΝΙΚΗ ΜΑΘΗΣΗ, Κ. ΔΙΑΜΑΝΤΑΡΑΣ, Δ. ΜΠΟΤΣΗΣ, ΚΛΕΙΔΑΡΙΘΜΟΣ, 2019, ΑΘΗΝΑ
2. ΝΕΥΡΩΝΙΚΑ ΔΙΚΤΥΑ ΚΑΙ ΜΗΧΑΝΙΚΗ ΜΑΘΗΣΗ, 3η ΕΚΔΟΣΗ, S. Haykin, Παπασωτηρίου, 2010, Αθήνα.