Università Roma Tre

Introduction to Artificial Intelligence and fields of application
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

Dive into deep learning
https://d2l.ai/

Introduction to optimization theory
Non-linear optimization: the problem of local minima
Preparation of data for correct training of the neural system
Supervised training: backpropagation algorithm for calculating the gradient of the error function of an MLP
Creation of the backpropagation algorithm in C/C++ from scratch
Gradient Descent training algorithm
Implementation of the Gradient Descent algorithm in C/C++ from scratch
Stochastic Gradient Descent training algorithm
Implementation of the Stochastic Gradient Descent algorithm in C/C++ from scratch
Levenberg-Marquardt training algorithm
Implementation of the Levenberg-Marquardt algorithm in C/C++ from scratch
Training with genetic algorithms and swarm intelligence
Unsupervised training
Reinforcement training

Dive into deep learning
https://d2l.ai/