Università Roma Tre

Artificial intelligence and fundamentals of machine learning. Types of artificial intelligence, classical AI system, definition of machine learning, classical approach and application areas. Fundamentals of machine learning, types of learning, training methods, generalization methods. Supervised learning for regression problems. Linear models, mean square error, learning as MSE minimization. Polynomial regression. Overfitting and underfitting. Examples of programming in Matlab and Python languages. Fundamental algorithms for supervised learning. Support vector machines, separation hyperplanes with soft-margin constraints, kernel tricks, and linearity. Machine learning decision trees, choice of attributes and values, entropy of information. Ensemble learning, parallel models, random forest. Learning with artificial neural networks. The perceptron. Multi-layer percepron (MLP) networks. Clustering with neural networks. Introduction to advanced deep learning architectures. Examples of programming in Matlab and Python languages. Data analysis, selection, and transformation. Image analysis, decomposition in YUV/YCbCr color spaces. Time/frequency data analysis, Fourier transform (outline), spectrograms. Examples of programming in Matlab and Python languages.

Lecture notes by the Professor on the Moodle platform and MS Teams of the University.
G. Barone, “Machine Learning e Intelligenza Artificiale: metodologie per lo sviluppo di sistemi automatici”, Dario Flaccovio Editore, 217 pp