- Oggetto:
- Oggetto:
Introduction to Deep Learning
- Oggetto:
Introduction to Deep Learning
- Oggetto:
Academic year 2021/2022
- Teaching staff
- Attilio Fiandrotti (Titolare del corso)
Prof. Rossella Cancelliere (Titolare del corso)
Valerio Basile (Titolare del corso)
Prof. Roberto Esposito (Titolare del corso)
Prof. 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 statistics for the theoretical parts; Python or structured programming for the labs
- 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:
Course delivery
Frontal lessons (with slides) with seminars and hands-on sessions with Keras on Google Colab.
- Oggetto:
Learning assessment methods
Students are required to discuss a project related to the topics addressed in the course.
- Oggetto:
Program
1) Introduction to Neural Networks (8h)
Introduction to machine learning and classical approaches: SVMs, decition trees, etc. (2h)
Lab: machine learning with Python and Sklearn (2h)Multilayer neural networks and learning with descent of backpropagated error gradient (2h)
Lab: exercises on training a simple neural network with Keras (with examples where gradients are applied automatically and manually) (2h)2) Convolutional and Deep Architectures (8h)
Convolutional neural networks (CNNs) and overview of deep convolutional architectures (2 h)
Lab: Image classification with CNNs using Keras (2 h)Autoencoders and adversarial learning (2 h)
Lab: Image generation using a GAN approach implemented with Keras (2h)3) Natural Language Processing (8h)
RNN: Recurrent Neural Networks, Long Short-term Memory, Gated Recurrent Unit, Transformer (2 h)
Natural language: Text classification with Keras (3 h)
Natural Language Generation (3 h)Suggested readings and bibliography
- Oggetto:
- Articolo
- Title:
- Deep learning
- Journal title:
- Nature
- Year of publication:
- 2015
- Author:
- Yann LeCun, Yoshua Bengio, Geoffrey Hinton
- Required:
- Si
- Oggetto:
- Libro
- Title:
- Deep learning. Vol. 1, no. 2. Cambridge: MIT press, 2016. https://www.deeplearningbook.org/
- Year of publication:
- 2016
- Publisher:
- MIT Press
- Author:
- Ian Goodfellow, Yoshua Bengio, Aaron Courville, Yoshua Bengio
- Required:
- No
- Oggetto:
.
- Oggetto:
More information
https://phd.i-learn.unito.it/login/index.php- Oggetto: