Directed Equilibrium Propagation Revisited
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, ye...
Saved in:
| Main Authors: | Pedro Costa, Pedro A. Santos |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-06-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/11/1866 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Training and synchronizing oscillator networks with Equilibrium Propagation
by: Théophile Rageau, et al.
Published: (2025-01-01) -
Research on SNN Learning Algorithms and Networks Based on Biological Plausibility
by: Bingqiang Huo, et al.
Published: (2025-01-01) -
Naturalized Epistemology and the Law of Evidence Revisited
by: Ronald J. Allen
Published: (2021-01-01) -
Dynamic analysis of malicious behavior propagation based on feature selection in software network
by: Huajian Xue, et al.
Published: (2024-11-01) -
Navigation in brain networks is possible using only local measures
by: Alex Hocking, et al.
Published: (2025-06-01)