Retrieval capabilities of hierarchical networks: from Dyson to Hopfield
Language
English
Status
Published
JCR Journal
JCR Journal
Journal
Issue/vol(year)
/114 (2015)
ISSN
0031-9007
Pages (printed)
028103
Date Issued
January 16, 2015
Subjects
Abstract
We consider statistical-mechanics models for spin systems built on hierarchical structures, which provide a simple example of non-mean-field framework. We show that the coupling decay with spin distance can give rise to peculiar features and phase diagrams much richer than their mean-field counterpart. In particular, we consider the Dyson model, mimicking ferromagnetism in lattices, and we prove the existence of a number of metastabilities, beyond the ordered state, which become stable in the thermodynamic limit. Such a feature is retained when the hierarchical structure is coupled with the Hebb rule for learning, hence mimicking the modular architecture of neurons, and gives rise to an associative network able to perform single pattern retrieval as well as multiple-pattern retrieval, depending crucially on the external stimuli and on the rate of interaction decay with distance; however, those emergent multitasking features reduce the network capacity with respect to the mean-field counterpart. The analysis is accomplished through statistical mechanics, Markov chain theory, signal-to-noise ratio technique, and numerical simulations in full consistency. Our results shed light on the biological complexity shown by real networks, and suggest future directions for understanding more realistic models.
Type
article
File(s)![]()
Name
Pubblicazione4_prl_Tavani.pdf
Description
Restricted file
Size
1.43 MB
Format
Adobe PDF
Checksum (MD5)
The MD5 message-digest algorithm can be used to verify the integrity of the file that you have uploaded. You can calculate its value locally via tools that are generally available in each operative system like md5sum
fa0ce989a40d2a2739ba04250c1bc8e0
