Sparsity, redundancy and robustness in artificial neural networks for learning and memory

Philippe Tigréat 1, 2
2 Lab-STICC_IMTA_CACS_IAS
Lab-STICC - Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance
Abstract : The objective of research in Artificial Intelligence (AI) is to reproduce human cognitive abilities by means of modern computers. The results of the last few years seem to announce a technological revolution that could profoundly change society. We focus our interest on two fundamental cognitive aspects, learning and memory. Associative memories offer the possibility to store information elements and to retrieve them using a sub-part of their content, thus mimicking human memory. Deep Learning allows to transition from an analog perception of the outside world to a sparse and more compact representation.In Chapter 2, we present a neural associative memory model inspired by Willshaw networks, with constrained connectivity. This brings an performance improvement in message retrieval and a more efficient storage of information.In Chapter 3, a convolutional architecture was applied on a task of reading partially displayed words under similar conditions as in a former psychology study on human subjects. This experiment put inevidence the similarities in behavior of the network with the human subjects regarding various properties of the display of words.Chapter 4 introduces a new method for representing categories usingneuron assemblies in deep networks. For problems with a large number of classes, this allows to reduce significantly the dimensions of a network.Chapter 5 describes a method for interfacing deep unsupervised networks with clique-based associative memories.
Liste complète des métadonnées

Cited literature [65 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-01812053
Contributor : Abes Star <>
Submitted on : Monday, June 11, 2018 - 10:54:40 AM
Last modification on : Wednesday, March 6, 2019 - 3:10:37 PM

File

2017IMTA0046_Tigreat-Philippe....
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01812053, version 1

Citation

Philippe Tigréat. Sparsity, redundancy and robustness in artificial neural networks for learning and memory. Neural and Evolutionary Computing [cs.NE]. Ecole nationale supérieure Mines-Télécom Atlantique, 2017. English. ⟨NNT : 2017IMTA0046⟩. ⟨tel-01812053⟩

Share

Metrics

Record views

338

Files downloads

515