Donnarumma, Francesco, Prevete, Roberto and Trautteur, Giuseppe (2012) Programming in the brain: a neural network theoretical framework. [Pubblicazione in rivista scientifica]
![[thumbnail of 09540091.2012.pdf]](http://www.fedoa.unina.it/style/images/fileicons/text.png "09540091.2012.pdf") |
Text
09540091.2012.pdf Visibile a [TBR] Repository staff only Download (9MB) |
| Item Type: | Pubblicazione in rivista scientifica |
|---|---|
| Resource language: | English |
| Title: | Programming in the brain: a neural network theoretical framework |
| Creators: | Creators Email Donnarumma, Francesco UNSPECIFIED Prevete, Roberto prevete@na.infn.it Trautteur, Giuseppe UNSPECIFIED |
| Date: | 2012 |
| Institution: | Università degli Studi di Napoli Federico II |
| Department: | Dipartimento di Scienze Fisiche |
| Original publication URL: | http://dx.doi.org/10.1080/09540091.2012.684670 |
| Journal or Publication Title: | Connection Science |
| Publisher: | Taylor & Francis |
| Date: | 2012 |
| ISSN: | 0954-0091 (print); 1360-0494 (online) |
| Volume: | Vol. 24, 71–90 |
| Number: | Nos. 2–3, June–September 2012 |
| Page Range: | pp. 71-90 |
| Keywords: | programmable neural networks; CTRNN; fixed-weight network; programmability; biologically plausible neural architecture |
| Access rights: | Restricted access |
| Additional information: | AIRobots |
| Date Deposited: | 12 Sep 2014 09:17 |
| Last Modified: | 17 May 2017 17:31 |
| URI: | http://www.fedoa.unina.it/id/eprint/9615 |
Collection description
Recent research shows that some brain areas perform more than one task and the switching times between them are incompatible with learning and that parts of the brain are controlled by other parts of the brain, or are “recycled”, or are used and reused for various purposes by other neural circuits in different task categories and cognitive domains. All this is conducive to the notion of “programming in the brain”. In this paper, we describe a programmable neural architecture, biologically plausible on the neural level, and we implement, test, and validate it in order to support the programming interpretation of the above-mentioned phenomenology.A programmable neural network is a fixed-weight network that is endowed with auxiliary or programming inputs and behaves as any of a specified class of neural networks when its programming inputs are fed with a code of the weight matrix of a network of the class. The construction is based on the “pulling out” of the multiplication between synaptic weights and neuron outputs and having it performed in “software” by specialised multiplicative-response fixed subnetworks. Such construction has been tested for robustness with respect to various sources of noise. Theoretical underpinnings, analysis of related research, detailed construction schemes, and extensive testing results are given.
Downloads
Downloads per month over past year
Actions (login required)
 |
View Item |
