DEEP LEARNING AND SCIENTIFIC COMPUTING (MOD. 1)
DEEP LEARNING AND SCIENTIFIC COMPUTING (MOD. 1)
| A.Y. | Credits |
|---|---|
| 2023/2024 | 4 |
| Lecturer | Office hours for students | |
|---|---|---|
| Valerio Freschi | Tuesday 11:00 - 13:00 or on demand |
| Teaching in foreign languages |
|---|
|
Course entirely taught in a foreign language
English
This course is entirely taught in a foreign language and the final exam can be taken in the foreign language. |
Assigned to the Degree Course
| Date | Time | Classroom / Location |
|---|
| Date | Time | Classroom / Location |
|---|
Learning Objectives
The teaching module aims to provide the elements necessary to understand the fundamentals of deep learning, with reference to training algorithms and some of the main state-of-the-art artificial neural network architectures.
Program
1. Introduction
1.1 Machine learning basics
1.2 The perceptron as a deep learning building block
1.3 Fully connected multilayer neural networks
2. Deep learning models training
2.1 Loss functions optimization
2.2 Gradient descent algorithm
2.3 Backpropagation
3. Deep learning architectures
3.1 Convolutional neural networks
3.2 Recurrent neural networks
Bridging Courses
There are no mandatory prerequisites.
Teaching Material
The teaching material prepared by the lecturer in addition to recommended textbooks (such as for instance slides, lecture notes, exercises, bibliography) and communications from the lecturer specific to the course can be found inside the Moodle platform › blended.uniurb.it
Teaching, Attendance, Course Books and Assessment
- Teaching
Theory lectures.
- Attendance
Although recommended, course attendance is not mandatory.
- Assessment
Oral exam on a topic agreed with the teacher.
- Disabilità e DSA
Le studentesse e gli studenti che hanno registrato la certificazione di disabilità o la certificazione di DSA presso l'Ufficio Inclusione e diritto allo studio, possono chiedere di utilizzare le mappe concettuali (per parole chiave) durante la prova di esame.
A tal fine, è necessario inviare le mappe, due settimane prima dell’appello di esame, alla o al docente del corso, che ne verificherà la coerenza con le indicazioni delle linee guida di ateneo e potrà chiederne la modifica.
| « back | Last update: 12/01/2024 |
