DRIEU, M. Nathan (2020) Reconnaissance des chiffres manuscrits par des réseaux de neurones : Etat de l'art et analyse paramétrique sur un cas restreint PRE - Research Project, ENSTA.



This internship was aiming at setting up an artificial intelligence based on neural networks able to recognize handwritten numerals and in analyzing their behaviour under various parameters. The MNIST dataset has been used to provide training and verification materials to networks. Two types of structures were studied; the first one is composed of fully-connected layers of neurons. The second one is called convolutional network with its main difference being analysing images through smaller parts. Then, different parameters were tested and performances were compared and analyzed in order to have a better understanding of neural networks behaviour. These experiments and analysis resulted in a knowledge source which could be used to apply neural networks to other problems.

Item Type:Thesis (PRE - Research Project)
Subjects:Information and Communication Sciences and Technologies
Mathematics and Applications
ID Code:8126
Deposited By:nathan Drieu
Deposited On:21 oct. 2020 11:04
Dernière modification:21 oct. 2020 11:04

Repository Staff Only: item control page