Donnarumma, Francesco
(2009)
A Model for Programmability and Virtuality in Dynamical Neural Networks.
[Tesi di dottorato]
(Inedito)
| Tipologia del documento: |
Tesi di dottorato
|
| Lingua: |
English |
| Titolo: |
A Model for Programmability and Virtuality in Dynamical Neural Networks |
| Autori: |
| Autore | Email |
|---|
| Donnarumma, Francesco | donnarumma@na.infn.it |
|
| Data: |
30 Novembre 2009 |
| Numero di pagine: |
218 |
| Istituzione: |
Università degli Studi di Napoli Federico II |
| Dipartimento: |
Matematica e applicazioni "Renato Caccioppoli" |
| Scuola di dottorato: |
Scienze matematiche e informatiche |
| Dottorato: |
Scienze computazionali e informatiche |
| Ciclo di dottorato: |
22 |
| Coordinatore del Corso di dottorato: |
| nome | email |
|---|
| Ricciardi, Luigi Maria | luigi.ricciardi@unina.ir |
|
| Tutor: |
| nome | email |
|---|
| Trautteur, Giuseppe | trau@na.infn.it |
|
| Data: |
30 Novembre 2009 |
| Numero di pagine: |
218 |
| Parole chiave: |
CTRNN, Fixed-weight networks, Neural dynamical systems, Programmability, Virtuality |
| Settori scientifico-disciplinari del MIUR: |
Area 01 - Scienze matematiche e informatiche > INF/01 - Informatica |
[error in script]
[error in script]
| Depositato il: |
04 Dic 2009 12:50 |
| Ultima modifica: |
10 Nov 2014 13:47 |
| URI: |
http://www.fedoa.unina.it/id/eprint/4293 |
| DOI: |
10.6092/UNINA/FEDOA/4293 |
Abstract
In this dissertation a fixed-weight architecture for Continuous Time Recurrent Neural Networks (CTRNNs) is proposed in order to give an account for biological phenomena, controlled by neuronal activity, in which changes of behavior occur so fast that presumably no changes in the involved neuronal connectivity are possible.
The proposed model possesses the following properties: a. the neural network variables have a direct biological interpretation; b. the change of behavior is controllable by auxiliary (programming) inputs; c. a single fixed-weight neural network has the capability to exhibit a wide repertoire of different behaviors given the appropriate auxiliary inputs. Such properties allow the model to be biologically plausible on the neural level and, at the same time, should sustain a programmability / virtuality capability usually associated only with the algorithmic, symbolic systems used in the high level functional modeling of biological systems.
A number of experiments are performed which corroborate: 1) the capability of the proposed architecture to be programmed with auxiliary inputs in order to reproduce the dynamical behaviors of networks with weight values coded by the auxiliary input; 2) the robustness of the proposed architecture w.r.t. variations of the I/O time scales.
Downloads per month over past year
Actions (login required)
 |
Modifica documento |
