Length: 10 hours - 2 cfu
Abstract:
The course aims at presenting biometric recognition approaches based on recent artificial intelligence techniques. In traditional biometric systems, the designer needs to develop algorithms to extract and compare sets of discriminative features from data. Approaches based on artificial intelligence can learn sets of discriminative features directly from multidimensional signals. The course presents biometric systems from a technological point of view and provides an excursus of approaches based on artificial intelligence, including: Feedforward Neural Networks, Convolutional Neural Networks, Autoencoders, and Deep Belief Neural Networks. Outline: 1) Biometric systems; 2) Artificial intelligence; 3) Biometric systems based on artificial intelligence techniques; 4) Design and implementation of biometric systems based on artificial intelligence techniques.
Dates & Venue
| Giorni | Aula | Orario |
Suggested Readings:
Lecturer:
Prof. Ruggero Donida Labati - Dipartimento di Informatica
Assessor:
Prof. Ruggero Donida Labati - Dipartimento di Informatica