Exploring subthreshold processing for next-generation TinyAI

The energy demands of modern AI systems have reached unprecedented levels, driven by the rapid scaling of deep learning models, including large language models, and the inefficiencies of current computational architectures. In contrast, biological neural systems operate with remarkable energy effici...

Full description

Saved in:
Bibliographic Details
Main Authors: Farid Nakhle, Antoine H. Harfouche, Hani Karam, Vasileios Tserolas
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Computational Neuroscience
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fncom.2025.1638782/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849411271565246464
author Farid Nakhle
Antoine H. Harfouche
Antoine H. Harfouche
Hani Karam
Vasileios Tserolas
author_facet Farid Nakhle
Antoine H. Harfouche
Antoine H. Harfouche
Hani Karam
Vasileios Tserolas
author_sort Farid Nakhle
collection DOAJ
description The energy demands of modern AI systems have reached unprecedented levels, driven by the rapid scaling of deep learning models, including large language models, and the inefficiencies of current computational architectures. In contrast, biological neural systems operate with remarkable energy efficiency, achieving complex computations while consuming orders of magnitude less power. A key mechanism enabling this efficiency is subthreshold processing, where neurons perform computations through graded, continuous signals below the spiking threshold, reducing energy costs. Despite its significance in biological systems, subthreshold processing remains largely overlooked in AI design. This perspective explores how principles of subthreshold dynamics can inspire the design of novel AI architectures and computational methods as a step toward advancing TinyAI. We propose pathways such as algorithmic analogs of subthreshold integration, including graded activation functions, dendritic-inspired hierarchical processing, and hybrid analog-digital systems to emulate the energy-efficient operations of biological neurons. We further explore neuromorphic and compute-in-memory hardware platforms that could support these operations, and propose a design stack aligned with the efficiency and adaptability of the brain. By integrating subthreshold dynamics into AI architecture, this work provides a roadmap toward sustainable, responsive, and accessible intelligence for resource-constrained environments.
format Article
id doaj-art-3a0b4a950d3046049e9afaba2b2e227f
institution Kabale University
issn 1662-5188
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Computational Neuroscience
spelling doaj-art-3a0b4a950d3046049e9afaba2b2e227f2025-08-20T03:34:49ZengFrontiers Media S.A.Frontiers in Computational Neuroscience1662-51882025-07-011910.3389/fncom.2025.16387821638782Exploring subthreshold processing for next-generation TinyAIFarid Nakhle0Antoine H. Harfouche1Antoine H. Harfouche2Hani Karam3Vasileios Tserolas4Department of Computer Science, Temple University, Japan Campus, Tokyo, JapanUnité de Formation et de Recherche en Sciences Économiques, Gestion, Mathématiques, et Informatique, Université Paris Nanterre, Nanterre, FranceFaculty of Business and Economics, American University of Science and Technology, Beirut, LebanonDepartment of Computer Science, Temple University, Japan Campus, Tokyo, JapanDepartment of Computer Science, Temple University, Japan Campus, Tokyo, JapanThe energy demands of modern AI systems have reached unprecedented levels, driven by the rapid scaling of deep learning models, including large language models, and the inefficiencies of current computational architectures. In contrast, biological neural systems operate with remarkable energy efficiency, achieving complex computations while consuming orders of magnitude less power. A key mechanism enabling this efficiency is subthreshold processing, where neurons perform computations through graded, continuous signals below the spiking threshold, reducing energy costs. Despite its significance in biological systems, subthreshold processing remains largely overlooked in AI design. This perspective explores how principles of subthreshold dynamics can inspire the design of novel AI architectures and computational methods as a step toward advancing TinyAI. We propose pathways such as algorithmic analogs of subthreshold integration, including graded activation functions, dendritic-inspired hierarchical processing, and hybrid analog-digital systems to emulate the energy-efficient operations of biological neurons. We further explore neuromorphic and compute-in-memory hardware platforms that could support these operations, and propose a design stack aligned with the efficiency and adaptability of the brain. By integrating subthreshold dynamics into AI architecture, this work provides a roadmap toward sustainable, responsive, and accessible intelligence for resource-constrained environments.https://www.frontiersin.org/articles/10.3389/fncom.2025.1638782/fulldendritic processingenergy efficiencygraded activationshybrid analog-digital systemsneuromorphic computingsubthreshold processing
spellingShingle Farid Nakhle
Antoine H. Harfouche
Antoine H. Harfouche
Hani Karam
Vasileios Tserolas
Exploring subthreshold processing for next-generation TinyAI
Frontiers in Computational Neuroscience
dendritic processing
energy efficiency
graded activations
hybrid analog-digital systems
neuromorphic computing
subthreshold processing
title Exploring subthreshold processing for next-generation TinyAI
title_full Exploring subthreshold processing for next-generation TinyAI
title_fullStr Exploring subthreshold processing for next-generation TinyAI
title_full_unstemmed Exploring subthreshold processing for next-generation TinyAI
title_short Exploring subthreshold processing for next-generation TinyAI
title_sort exploring subthreshold processing for next generation tinyai
topic dendritic processing
energy efficiency
graded activations
hybrid analog-digital systems
neuromorphic computing
subthreshold processing
url https://www.frontiersin.org/articles/10.3389/fncom.2025.1638782/full
work_keys_str_mv AT faridnakhle exploringsubthresholdprocessingfornextgenerationtinyai
AT antoinehharfouche exploringsubthresholdprocessingfornextgenerationtinyai
AT antoinehharfouche exploringsubthresholdprocessingfornextgenerationtinyai
AT hanikaram exploringsubthresholdprocessingfornextgenerationtinyai
AT vasileiostserolas exploringsubthresholdprocessingfornextgenerationtinyai