The course aims to introduce students to the field of artificial intelligence starting from the study of basic algorithms in their intimate nature. After an initial overview of the state of the art, the student will be guided in the low-level study of the functioning of machine learning algorithms to then be able to develop prediction mechanisms even for higher levels of abstraction. At the end of the course, the student will be able to analyse, design and create an Artificial Intelligence system applied to a specific problem.
teacher profile teaching materials
Theoretical principles and mathematical foundations of Artificial Intelligence
Main Artificial Intelligence algorithms
Supervised neural networks: the multilayer perceptron (MLP) and synaptic weight matrices
Application of an MLP in Matlab and Python for interpolation and approximation (nonlinear regression).
Setting up an external server for low-level programming
Creating an MLP in C/C++ from scratch
Convolutional Neural Networks (CNN): Design in Matlab and Python
Building a CNN in C/C++ from scratch
Recursive Neural Networks (RNN): Design in Matlab and Python
Building an RNN in C/C++ from scratch
Generative Adversarial Neural Networks (GANs): Design in Matlab and Python
Building a GAN in C/C++ from scratch
Unsupervised neural networks
Neural networks with reinforcement learning
https://d2l.ai/
Mutuazione: 20810549-1 ARTIFICIAL INTELLIGENCE: ALGORITHMS AND METHODS in Ingegneria delle Telecomunicazioni LM-27 RIGANTI FULGINEI FRANCESCO
Programme
Introduction to Artificial Intelligence and fields of applicationTheoretical principles and mathematical foundations of Artificial Intelligence
Main Artificial Intelligence algorithms
Supervised neural networks: the multilayer perceptron (MLP) and synaptic weight matrices
Application of an MLP in Matlab and Python for interpolation and approximation (nonlinear regression).
Setting up an external server for low-level programming
Creating an MLP in C/C++ from scratch
Convolutional Neural Networks (CNN): Design in Matlab and Python
Building a CNN in C/C++ from scratch
Recursive Neural Networks (RNN): Design in Matlab and Python
Building an RNN in C/C++ from scratch
Generative Adversarial Neural Networks (GANs): Design in Matlab and Python
Building a GAN in C/C++ from scratch
Unsupervised neural networks
Neural networks with reinforcement learning
Core Documentation
Dive into deep learninghttps://d2l.ai/
Attendance
Attendance is optional but highly recommended.Type of evaluation
Design and implementation of a machine learning model