NEURAL COMPUTING

INF/01 - 6 CFU - 1° semestre

Docente titolare dell'insegnamento

SEBASTIANO BATTIATO
Email: battiato@dmi.unict.it
Edificio / Indirizzo: Dipartimento di Matematica e Informatica - Viale Andrea Doria 6
Telefono: +390957383206
Orario ricevimento: Consultare il sito web del docente (See personal home page)


Obiettivi formativi

The course covers the theory and practice of artificial neural networks, highlighting their relevance both for artificial intelligence applications and for modeling human cognition and brain function. Theoretical discussion of various types of neural networks and learning algorithms is complemented by hands-on practices in the computer lab. Models for classification and regression, as well as neural network architectures (e.g., Deep Learning) will be discussed. The course will present the techniques to design and optimize learning algorithms, and those useful to assess the performance of Machine Learning systems.


Modalità di svolgimento dell'insegnamento

The main teaching methods are as follows:

Should teaching be carried out in mixed mode or remotely, it may be necessary to introduce changes with respect to previous statements, in line with the programme planned and outlined in the syllabus.


Prerequisiti richiesti

Basic Calculus anf Math

Algebra and Matrix Notation

Machine learning basic principle

Python programming language



Frequenza lezioni

Strongly reccomended



Contenuti del corso

Linear Models for Regression: Linear Models for Classification: Gradient Descent, Multi-Class Classification, Classifiers Evaluation

Neural models and Network Architectures

Basic neural network models: multilayer perceptron, distance or similarity based neural networks, associative memory and self-organizing feature map, radial basis function based multilayer perceptron, neural network decision trees, etc.

Basic learning algorithms: the delta learning rule, the back propagation algorithm, self-organization learning, etc.

Supervised Learning with Neural Networks

Deep Learning: Convolutional Neural Network

Python programming and Python Libraries for Machine Learning



Testi di riferimento

DEEP LEARNING FROM BASICS TO PRACTICE (2020)

https://www.glassner.com/portfolio/deep-learning-from-basics-to-practice/

Dive into Deep Learning (2020)

https://d2l.ai/d2l-en.pdf

OTHER

E. Alpaydin, “Introduction to Machine Learning”, MIT Press, 2014

I. Goodfellow, Y. Bengio and A. Courville, "Deep Learning", MIT Press, 2016

M. P. Deisenroth, A A. Faisal, and C. Soon On, Mathematics for Machine Learning, MIT Press, 2019


Altro materiale didattico

Course notes

Script and code provided by the teacher

Video Material (on line courses)



Programmazione del corso

 ArgomentiRiferimenti testi
1Logistic RegressionGlassner (vol .1, vol 2) 
2BacKpropagationGlassner (vol .1, vol 2) 
3Supervised vs Unsupervised LearningGlassner (vol .1, vol 2) 
4Neural Network principlesBishop 
5Convolutional Neural NetworksDive into Deep Learning 


Verifica dell'apprendimento


MODALITÀ DI VERIFICA DELL'APPRENDIMENTO

Writtten and Oral Examination

Learning assessment may also be carried out on line, should the conditions require it.


ESEMPI DI DOMANDE E/O ESERCIZI FREQUENTI

Example of Algorithms based on training data

Cross Validation

NN Architecutre




Apri in formato Pdf English version