Deep Gated Hebbian Predictive Coding Accounts for Emergence of Complex Neural Response Properties Along the Visual Cortical Hierarchy
Predictive coding provides a computational paradigm for modeling perceptual processing as the construction of representations accounting for causes of sensory inputs. Here, we developed a scalable, deep network architecture for predictive coding that is trained using a gated Hebbian learning rule an...
Main Authors: | Shirin Dora, Sander M. Bohte, Cyriel M. A. Pennartz |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2021-07-01
|
Series: | Frontiers in Computational Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fncom.2021.666131/full |
Similar Items
-
Multimodal Representation Learning for Place Recognition Using Deep Hebbian Predictive Coding
by: Martin J. Pearson, et al.
Published: (2021-12-01) -
Predictive coding with spiking neurons and feedforward gist signaling
by: Kwangjun Lee, et al.
Published: (2024-04-01) -
Local minimization of prediction errors drives learning of invariant object representations in a generative network model of visual perception
by: Matthias Brucklacher, et al.
Published: (2023-09-01) -
Learning cortical hierarchies with temporal Hebbian updates
by: Pau Vilimelis Aceituno, et al.
Published: (2023-05-01) -
Complementary networks of cortical somatostatin interneurons enforce layer specific control
by: Alexander Naka, et al.
Published: (2019-03-01)