"G. d'Annunzio"
The student must have the basic notions of calculus and linear algebra.
The educational goal is the following:
Knowledge and understanding
The course aims at giving a basic knowledge of the main type of deep neural network, i.e. feedforward networks. To this end the course will also supply the necessary notions of probability.
Ability to apply knowledge and understanding
Et the end of the course students must be able to to carry out a project on some application that will be assigned by the teacher; the methods that have been employed and the results that have been obtained will be discussed with the teacher.
It is expected that the ability to use feedforward neural networks is used in professional contexts, for various purposes, but possibly also in public administration or in research activities.
Feedforward deep neural networks, convolutional networks and possibly recurrent networks
1. Elements of probability 2.Fundamentals of machine learning 3.Feedforward deep neural networks 4. Convolutional networks 5. Recurrent networks (possibly) 6. Applications
Goodfellow, I.; Bengio, Y.; Courville, A.: Deep learning, MIT Press (2016)
M. Nielsen: Neural Networks and Deep Learning, available at http://neuralnetworksanddeeplearning.com
Lectures and programming lab.
La conoscenza e capacità di comprensione raggiunta dallo studente verrà verificata attraverso il progetto finale assegnato dal docente e un colloquio in cui verranno discusse le metodologie scelte e i risultati ottenuti.
Knowledge and understanding will be tested by the final project assigned by the teacher and by an oral exam in which the methods that have been employed and the results that have been obtained in the project will be discussed.
The ability to apply knowledge and understanding will be tested by the final project assigned by the teacher and by an oral exam in which the methods that have been employed and the results that have been obtained in the project will be discussed.
The final grade will be on the scale of 1 to 30.
