This is a laboratory module with some hints at theoretical basis. First, an introduction to the development environment chosen, i.e. the Anaconda package. Second, some basic concepts about object-orientation. Afterwards, some considerations about the design of a neural network as a class and the main blocks of the code. A glance follows at the datasets and how they have been scaled in order to improve performance. Then a hint about possible future developments of the code in sight of deep networks and, finally, some indications about running the sample code.
Deep Learning 03 - Laboratory - Mafalda Neural Network code
Cristina De Castro
2018
Abstract
This is a laboratory module with some hints at theoretical basis. First, an introduction to the development environment chosen, i.e. the Anaconda package. Second, some basic concepts about object-orientation. Afterwards, some considerations about the design of a neural network as a class and the main blocks of the code. A glance follows at the datasets and how they have been scaled in order to improve performance. Then a hint about possible future developments of the code in sight of deep networks and, finally, some indications about running the sample code.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


