This course covers the basics of deep learning. Starting from the simple artificial neuron (perceptron), we will introduce artificial neural networks and their most common architectures, such as fully connected and convolutional models. Then, we will see how these networks learn to accomplish specific tasks from data. Back propagation and optimization of the loss function will be explained together with the standard pipeline to train, validate, and test these models. We will also introduce some basic concepts of unsupervised deep learning.
From 2020 to 2023, Cristiano De Nobili also taught in this course.
