Multiscale nonlinear integration drives accurate encoding of input information

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nicoletti, Giorgio, Busiello, Daniel M.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909394545934336
author Nicoletti, Giorgio
Busiello, Daniel M.
author_facet Nicoletti, Giorgio
Busiello, Daniel M.
contents Biological and artificial systems encode information through several complex nonlinear operations, making their exact study a formidable challenge. These internal mechanisms often take place across multiple timescales and process external signals to enable functional output responses. In this work, we focus on two widely implemented paradigms: nonlinear summation, where signals are first processed independently and then combined; and nonlinear integration, where they are combined first and then processed. We study a general model where the input signal is propagated to an output unit through a processing layer via nonlinear activation functions. Further, we distinguish between the two cases of fast and slow processing timescales. We demonstrate that integration and fast-processing capabilities systematically enhance input-output mutual information over a wide range of parameters and system sizes, while simultaneously enabling tunable input discrimination. Moreover, we reveal that high-dimensional embeddings and low-dimensional projections emerge naturally as optimal competing strategies. Our results uncover the foundational features of nonlinear information processing with profound implications for both biological and artificial systems.
format Preprint
id arxiv_https___arxiv_org_abs_2411_11710
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multiscale nonlinear integration drives accurate encoding of input information
Nicoletti, Giorgio
Busiello, Daniel M.
Statistical Mechanics
Biological and artificial systems encode information through several complex nonlinear operations, making their exact study a formidable challenge. These internal mechanisms often take place across multiple timescales and process external signals to enable functional output responses. In this work, we focus on two widely implemented paradigms: nonlinear summation, where signals are first processed independently and then combined; and nonlinear integration, where they are combined first and then processed. We study a general model where the input signal is propagated to an output unit through a processing layer via nonlinear activation functions. Further, we distinguish between the two cases of fast and slow processing timescales. We demonstrate that integration and fast-processing capabilities systematically enhance input-output mutual information over a wide range of parameters and system sizes, while simultaneously enabling tunable input discrimination. Moreover, we reveal that high-dimensional embeddings and low-dimensional projections emerge naturally as optimal competing strategies. Our results uncover the foundational features of nonlinear information processing with profound implications for both biological and artificial systems.
title Multiscale nonlinear integration drives accurate encoding of input information
topic Statistical Mechanics
url https://arxiv.org/abs/2411.11710