Event-driven eligibility propagation in large sparse networks: efficiency shaped by biological realism
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912731052900352 |
|---|---|
| author | Korcsak-Gorzo, Agnes Valverde, Jesús A. Espinoza Stapmanns, Jonas Plesser, Hans Ekkehard Dahmen, David Bolten, Matthias van Albada, Sacha J. Diesmann, Markus |
| author_facet | Korcsak-Gorzo, Agnes Valverde, Jesús A. Espinoza Stapmanns, Jonas Plesser, Hans Ekkehard Dahmen, David Bolten, Matthias van Albada, Sacha J. Diesmann, Markus |
| contents | Despite remarkable technological advances, AI systems may still benefit from biological principles, such as recurrent connectivity and energy-efficient mechanisms. Drawing inspiration from the brain, we present a biologically plausible extension of the eligibility propagation (e-prop) learning rule for recurrent spiking networks. By translating the time-driven update scheme into an event-driven one, we integrate the learning rule into a simulation platform for large-scale spiking neural networks and demonstrate its applicability to tasks such as neuromorphic MNIST. We extend the model with prominent biological features such as continuous dynamics and weight updates, strict locality, and sparse connectivity. Our results show that biologically grounded constraints can inform the design of computationally efficient AI algorithms, offering scalability to millions of neurons without compromising learning performance. This work bridges machine learning and computational neuroscience, paving the way for sustainable, biologically inspired AI systems while advancing our understanding of brain-like learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_21674 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Event-driven eligibility propagation in large sparse networks: efficiency shaped by biological realism Korcsak-Gorzo, Agnes Valverde, Jesús A. Espinoza Stapmanns, Jonas Plesser, Hans Ekkehard Dahmen, David Bolten, Matthias van Albada, Sacha J. Diesmann, Markus Neural and Evolutionary Computing Neurons and Cognition Despite remarkable technological advances, AI systems may still benefit from biological principles, such as recurrent connectivity and energy-efficient mechanisms. Drawing inspiration from the brain, we present a biologically plausible extension of the eligibility propagation (e-prop) learning rule for recurrent spiking networks. By translating the time-driven update scheme into an event-driven one, we integrate the learning rule into a simulation platform for large-scale spiking neural networks and demonstrate its applicability to tasks such as neuromorphic MNIST. We extend the model with prominent biological features such as continuous dynamics and weight updates, strict locality, and sparse connectivity. Our results show that biologically grounded constraints can inform the design of computationally efficient AI algorithms, offering scalability to millions of neurons without compromising learning performance. This work bridges machine learning and computational neuroscience, paving the way for sustainable, biologically inspired AI systems while advancing our understanding of brain-like learning. |
| title | Event-driven eligibility propagation in large sparse networks: efficiency shaped by biological realism |
| topic | Neural and Evolutionary Computing Neurons and Cognition |
| url | https://arxiv.org/abs/2511.21674 |