Weight versus Node Perturbation Learning in Temporally Extended Tasks: Weight Perturbation Often Performs Similarly or Better
Biological constraints often impose restrictions on plasticity rules such as locality and reward-based rather than supervised learning. Two learning rules that comply with these restrictions are weight (WP) and node (NP) perturbation. NP is often used in learning studies, in particular, as a benchma...
Main Authors: | Paul Züge, Christian Klos, Raoul-Martin Memmesheimer |
---|---|
Format: | Article |
Language: | English |
Published: |
American Physical Society
2023-04-01
|
Series: | Physical Review X |
Online Access: | http://doi.org/10.1103/PhysRevX.13.021006 |
Similar Items
-
Orthogonal Polynomials with Singularly Perturbed Freud Weights
by: Chao Min, et al.
Published: (2023-05-01) -
On Certain Properties and Applications of the Perturbed Meixner–Pollaczek Weight
by: Abey S. Kelil, et al.
Published: (2021-04-01) -
Towards Certificated Model Robustness Against Weight Perturbations
by: Weng, Tsui-Wei, et al.
Published: (2022) -
Study of Sensitivity to Weight Perturbation for Convolution Neural Network
by: Lin Xiang, et al.
Published: (2019-01-01) -
WEIGHTED RIESZ BASES IN G-FUSION FRAMES AND THEIR PERTURBATION
by: Gh. Rahimlou, et al.
Published: (2020-01-01)