Saved in:
Bibliographic Details
Main Authors: Golmohammadi, Arash, Luboeinski, Jannik, Tetzlaff, Christian
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.05126
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908682700193792
author Golmohammadi, Arash
Luboeinski, Jannik
Tetzlaff, Christian
author_facet Golmohammadi, Arash
Luboeinski, Jannik
Tetzlaff, Christian
contents Heterogeneity is a ubiquitous property of many biological systems and has profound implications for computation. While it is conceivable to optimize neuronal and synaptic heterogeneity for a specific task, such top-down optimization is biologically implausible, prone to catastrophic forgetting, and both data- and energy-intensive. In contrast, biological organisms, with remarkable capacity to perform numerous tasks with minimal metabolic cost, exhibit a heterogeneity that is inherent, stable during adulthood, and task-unspecific. Inspired by this intrinsic form of heterogeneity, we investigate the utility of variations in neuronal time constants for solving hundreds of distinct temporal tasks of varying complexity. Our results show that intrinsic heterogeneity significantly enhances performance and robustness in an implementation-independent manner, indicating its usefulness for both (rate-based) machine learning and (spike-coded) neuromorphic applications. Importantly, only skewed heterogeneity profiles-reminiscent of those found in biology-produce such performance gains. We further demonstrate that this computational advantage eliminates the need for large networks, allowing comparable performance with substantially lower operational, metabolic, and energetic costs, respectively in silico, in vivo, and on neuromorphic hardware. Finally, we discuss the implications of intrinsic (rather than task-induced) heterogeneity for the design of efficient artificial systems, particularly novel neuromorphic devices that exhibit similar device-to-device variability.
format Preprint
id arxiv_https___arxiv_org_abs_2412_05126
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Skewed Neuronal Heterogeneity Enhances Efficiency On Various Computing Systems
Golmohammadi, Arash
Luboeinski, Jannik
Tetzlaff, Christian
Machine Learning
Neural and Evolutionary Computing
Heterogeneity is a ubiquitous property of many biological systems and has profound implications for computation. While it is conceivable to optimize neuronal and synaptic heterogeneity for a specific task, such top-down optimization is biologically implausible, prone to catastrophic forgetting, and both data- and energy-intensive. In contrast, biological organisms, with remarkable capacity to perform numerous tasks with minimal metabolic cost, exhibit a heterogeneity that is inherent, stable during adulthood, and task-unspecific. Inspired by this intrinsic form of heterogeneity, we investigate the utility of variations in neuronal time constants for solving hundreds of distinct temporal tasks of varying complexity. Our results show that intrinsic heterogeneity significantly enhances performance and robustness in an implementation-independent manner, indicating its usefulness for both (rate-based) machine learning and (spike-coded) neuromorphic applications. Importantly, only skewed heterogeneity profiles-reminiscent of those found in biology-produce such performance gains. We further demonstrate that this computational advantage eliminates the need for large networks, allowing comparable performance with substantially lower operational, metabolic, and energetic costs, respectively in silico, in vivo, and on neuromorphic hardware. Finally, we discuss the implications of intrinsic (rather than task-induced) heterogeneity for the design of efficient artificial systems, particularly novel neuromorphic devices that exhibit similar device-to-device variability.
title Skewed Neuronal Heterogeneity Enhances Efficiency On Various Computing Systems
topic Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2412.05126