Multimodal Physical Learning in Brain-Inspired Iontronic Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Conte, Monica, van Roij, René, Dijkstra, Marjolein
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908633023905792
author Conte, Monica
van Roij, René
Dijkstra, Marjolein
author_facet Conte, Monica
van Roij, René
Dijkstra, Marjolein
contents Inspired by the brain, we present a physical alternative to traditional digital neural networks -- a microfluidic network in which nodes are connected by conical, electrolyte-filled channels acting as memristive iontronic synapses. Their electrical conductance responds not only to electrical signals, but also to chemical, mechanical, and geometric changes. Leveraging this multimodal responsiveness, we develop a training algorithm where learning is achieved by altering either the channel geometry or the applied stimuli. The network performs forward passes physically via ionic relaxation, while learning combines this physical evolution with numerical gradient descent. We theoretically demonstrate that this system can perform tasks like input-output mapping and linear regression with bias, paving the way for soft, adaptive materials that compute and learn without conventional electronics.
format Preprint
id arxiv_https___arxiv_org_abs_2511_04209
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multimodal Physical Learning in Brain-Inspired Iontronic Networks
Conte, Monica
van Roij, René
Dijkstra, Marjolein
Soft Condensed Matter
Inspired by the brain, we present a physical alternative to traditional digital neural networks -- a microfluidic network in which nodes are connected by conical, electrolyte-filled channels acting as memristive iontronic synapses. Their electrical conductance responds not only to electrical signals, but also to chemical, mechanical, and geometric changes. Leveraging this multimodal responsiveness, we develop a training algorithm where learning is achieved by altering either the channel geometry or the applied stimuli. The network performs forward passes physically via ionic relaxation, while learning combines this physical evolution with numerical gradient descent. We theoretically demonstrate that this system can perform tasks like input-output mapping and linear regression with bias, paving the way for soft, adaptive materials that compute and learn without conventional electronics.
title Multimodal Physical Learning in Brain-Inspired Iontronic Networks
topic Soft Condensed Matter
url https://arxiv.org/abs/2511.04209