Feature, Configuration, History : a bio-inspired framework for information representation in neural networks

Frédéric Alexandre 1, 2, 3, * Maxime Carrere 1, 2, 3 Randa Kassab 1, 2, 3
* Corresponding author
1 Mnemosyne - Mnemonic Synergy
LaBRI - Laboratoire Bordelais de Recherche en Informatique, Inria Bordeaux - Sud-Ouest, IMN - Institut des Maladies Neurodégénératives [Bordeaux]
Abstract : Artificial Neural Networks are very efficient adaptive models but one of their recognized weaknesses is about information representation, often carried out in an input vector without a structure. Beyond the classical elaboration of a hierarchical representation in a series of layers, we report here inspiration from neuroscience and argue for the design of heterogenous neural networks, processing information at feature, configuration and history levels of granularity, and interacting very efficiently for high-level and complex decision making. This framework is built from known characteristics of the sensory cortex, the hippocampus and the prefrontal cortex and is exemplified here in the case of pavlovian conditioning, but we propose that it can be advantageously applied in a wider extent, to design flexible and versatile information processing with neuronal computation.
Document type :
Conference papers
Complete list of metadatas

Cited literature [26 references]  Display  Hide  Download

https://hal.inria.fr/hal-01095036
Contributor : Frédéric Alexandre <>
Submitted on : Sunday, December 14, 2014 - 10:57:50 PM
Last modification on : Friday, May 10, 2019 - 1:54:01 PM
Long-term archiving on : Sunday, March 15, 2015 - 10:22:04 AM

File

NCTA_Alexandre14.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01095036, version 1

Citation

Frédéric Alexandre, Maxime Carrere, Randa Kassab. Feature, Configuration, History : a bio-inspired framework for information representation in neural networks. International Conference on Neural Computation Theory and Applications, Oct 2014, Rome, Italy. ⟨hal-01095036⟩

Share

Metrics

Record views

607

Files downloads

255