Directed Equilibrium Propagation Revisited

Pedro Costa () and Pedro A. Santos ()
Additional contact information
Pedro Costa: Instituto Superior Técnico, University of Lisbon, 1049-001 Lisbon, Portugal
Pedro A. Santos: Instituto Superior Técnico, University of Lisbon, 1049-001 Lisbon, Portugal

Mathematics, 2025, vol. 13, issue 11, 1-19

Abstract: Equilibrium Propagation (EP) offers a biologically inspired alternative to backpropagation for training recurrent neural networks, but its reliance on symmetric feedback connections and stability limitations hinders practical adoption. The DirEcted EP (DEEP) model relaxes the symmetry constraint, yet suffers from convergence issues and lacks a principled learning guarantee. In this work, we generalize DEEP by incorporating neuronal leakage, providing new convergence criteria for the network’s dynamics. We additionally propose a novel local learning rule closely linked to the objective function’s gradient and establish sufficient conditions for reliable learning in small networks. Our results resolve longstanding stability challenges and bring energy-based learning models closer to biologically plausible and provably effective neural computation.

Keywords: recurrent neural networks; equilibrium propagation; biologically plausible algorithms (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/11/1866/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/11/1866/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:11:p:1866-:d:1670885

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().