- Oggetto:
- Oggetto:
Introduction to Deep Learning
- Oggetto:
Introduction to Deep Learning
- Oggetto:
Academic year 2023/2024
- Teachers
- Attilio Fiandrotti (Titolare del corso)
Rossella Cancelliere (Titolare del corso)
Valerio Basile (Titolare del corso)
Roberto Esposito (Titolare del corso)
Marco Botta (Titolare del corso) - Degree course
- PhD in Computer Science
- Year
- 1st year, 2nd year, 3rd year
- Teaching period
- Seminario
- Type
- A scelta dello studente, Seminario
- Credits/Recognition
- 6
- Course disciplinary sector (SSD)
- INF/01 - informatics
- Delivery
- Tradizionale
- Language
- Inglese
- Attendance
- Obbligatoria
- Type of examination
- Relazione finale
- Prerequisites
- Basic maths and statistics for the theoretical parts; Structured programming for the labs, some basics in Python will help but are not mandatory
- Oggetto:
Sommario del corso
- Oggetto:
Course objectives
Deep learning based approaches outperform traditional approaches in a number of applications spanning from data analysis to image processing and natural language processing. The availability of large sets of annotated data, powerful yet affordable parallel computers and improved optimization techniques are behind this revolution. This course will provide first an introduction to multilayer neural networks and its cornerstones such as learning with descent of the backpropagated error gradient. Next, convolutional and deep architectures will be introduced in the context of image processing, Finally, the course will look into recurrent architectures for time series and natural language processing.
- Oggetto:
Program
Day
Time
Lecturer
Topic
5/2
11-13
Esposito R.
Multilayer neural networks and learning with descent of backpropagated error gradient
7/2
11-13
Esposito R.
Lab: exercises on training a simple neural network with Keras with examples where gradients are applied automatically and manually (*)
8/2
14-16
Fiandrotti A.
Convolutional neural networks (CNNs) and overview of deep convolutional architectures
9/2
11-13
Fiandrotti A.
Object detection with CNNs and lab in image classification with CNNs using Keras
12/2
11-13
Polato M.
Introduction to Graph Neural Networks (GNNs)
13/2
11-13
Esposito R.
Autoencoders and adversarial learning
15/2
14-16
Esposito R.
Lab: Image generation using a GAN approach with Keras
16/2
14-15
Tartaglione E.
Seminar: pruning neural networks
16/2
15-17
Cancelliere R.
RNN: Recurrent Neural Networks, Long Short-term Memory, Gated Recurrent Unit
19/2
11-13
Basile V.
Natural language: Text classification with Keras
20/2
11-13
Cancelliere R.
Natural Language Generation with RNNs
26/2
11-13
Basile V.
Transformer networks for Natural Language Processing (NLP)
27/2
11-13
Basile V.
Large Language Models (LLMs) for NLP
- Oggetto:
Course delivery
Frontal lessons (with slides) with seminars and hands-on sessions with Keras on Google Colab.
All lectures will be given in via Pessinetto 12, "Sala conferenze" at the third floor unless otherwise indicated (* contact the lecturer)- Oggetto:
Learning assessment methods
Students are required to discuss a project related to the topics addressed in the course.
Suggested readings and bibliography
- Oggetto:
.
- Oggetto:
Further information
https://phd.i-learn.unito.it/login/index.php- Enroll
- Closed
- Enrollment opening date
- 01/01/2024 at 00:00
- Enrollment closing date
- 29/02/2024 at 23:55
- Oggetto:
