Artificial Neural Networks architectures and computational paradigm
Supervised and unsupervised learning
Classification of Artificial Neural Networks and Learning Methods 
The biological neuron and the artificial neuron: weights and activation functions.
Artificial Neural Networks as universal approximators
Static, dynamic and recurrent networs
Perceptron and Multilayer Feedforward networks: the back-propagation algorithm
Learning and generalization
Support Vector Machines
Applications of Artificial Neural Networks and Support Vector Machines.

Software for Artificial Neural Networks (Conda, Python)

Objectives

D1 - Knowledge and understanding
1. Understand the concepts and techniques of Artificial Neural Networks through the study of the most important neural network models.


D2 - Applying knowledge and understanding
1. Develop problem solving skills through the analysis of problem statements and determining the most appropriate solution model
2. Implement standard learning algorithms and utilize standard software for Artificial Neural Networks.

D3 - Making judgements
1. Acquire sufficient theoretical background to be able to reason about the behavior of Artificial Neural Networks. 
2. Critically analyze Artificial Neural Network systems and their application;

D4 - Communication skills
1 Discuss the main aspect of Artificial Neural Network models
2 Correctly utilize the basic terminology related to an artificial neuron

D5 - Learning skills
1. Deepen through personal study, the most recent aspects of Artificial Neural Networks
2. Design and implement machine-learning system.
3. Work in groups developing small projects

Prerequisites

Linear and nonlinear programming

Teaching Methods

The course consists of lectures and guided projects. In particular, the projects will be devoted to the solution of classification and pattern recognition problems using Artificial Neural Networks and Support Vector Machines software

Verification of learning

Final oral exam. Project work. Examination sessions are provided in February, June/July, andSeptember/October. The exams scheduled in December and April are reserved to “fuori corso”. There are no exam sessions during the teaching period.

Texts

Hertz, Krogh, Palmer "Introductions to the theory of Neural Computation", Addison-Wesley 1991
Xiang-Sun Zhang “Neural Networks in Optimization", Springer, 2000
Artificial Neural Networks http://en.wikibooks.org/wiki/Artificial_Neural_Networks

Kriesel "A Brief Introduction to Neural Networks" http://www.dkriesel.com/en/science/neural_networks

Additional study material will be available from the teacher

Latest News