DANA: Distributed numerical and adaptive modelling framework

Nicolas P. Rougier, Jérémy Fix
Network: Computation in Neural Systems. 2012-09-20; 23(4): 237-253
DOI: 10.3109/0954898X.2012.721573

Lire sur PubMed

1. Network. 2012;23(4):237-53. doi: 10.3109/0954898X.2012.721573. Epub 2012 Sep 20.

DANA: distributed numerical and adaptive modelling framework.

Rougier NP(1), Fix J.

Author information:
(1)INRIA Bordeaux - Sud Ouest, 351, Cours de la Libération, 33405 Talence Cedex,

DANA is a python framework ( http://dana.loria.fr ) whose computational paradigm
is grounded on the notion of a unit that is essentially a set of time dependent
values varying under the influence of other units via adaptive weighted
connections. The evolution of a unit’s value are defined by a set of differential
equations expressed in standard mathematical notation which greatly ease their
definition. The units are organized into groups that form a model. Each unit can
be connected to any other unit (including itself) using a weighted connection.
The DANA framework offers a set of core objects needed to design and run such
models. The modeler only has to define the equations of a unit as well as the
equations governing the training of the connections. The simulation is completely
transparent to the modeler and is handled by DANA. This allows DANA to be used
for a wide range of numerical and distributed models as long as they fit the
proposed framework (e.g. cellular automata, reaction-diffusion system,
decentralized neural networks, recurrent neural networks, kernel-based image
processing, etc.).

DOI: 10.3109/0954898X.2012.721573
PMID: 22994650 [Indexed for MEDLINE]

Auteurs Bordeaux Neurocampus