Local learning is all you need: brain-aligned predictive coding networks
Abstract
Predictive Coding (PC) is an influential account of how brain representations emerge through hierarchical, local, self-supervised prediction-based learning, without requiring globally propagated error signals. Despite extensive evidence supporting PC, a striking paradox persists: computational models built on these biologically grounded principles have consistently failed to match state-of-the-art Deep Neural Networks in performance and brain-alignment. Here, we show that this paradox can be overcome. We introduce Predictive Brain Networks (PBNs), a hierarchical recurrent framework that implements local PC-based learning and achieves representational alignment with the human ventral visual stream matching or exceeding established vision models. Importantly, PBN top-down predictions encode unique, brain-aligned information not captured during bottom-up feature extraction, with this contribution increasing in locally trained variants. Further, PBNs substantially outperform existing PC-inspired networks on downstream classification tasks, reproduce key signatures of PC (with higher-level predictions shaping lower-level visual responses as observed in the primate cortex), and support uncertainty estimation. PBNs therefore close a longstanding gap in computational neuroscience by combining two properties that have been largely separated: the brain-inspired learning mechanisms of predictive coding and the representational power of modern deep networks. They provide a scalable framework for studying biologically grounded learning without sacrificing the capacity to produce rich neural representations.
Related
- Predictive learning with local plasticity in excitatory-inhibitory networks
- Predictive coding networks capture human neural representations missing in supervised DNNs
- Selective Hippocampal Reactivation Driven by Neocortical Feedback Supports Memory Transfer in Predictive-Coding Networks
- Multi-agent meta-reinforcement learning based on contrastive predictive coding—For rapid adaptive traffic control after emergencies
- Prospective Coding Improves Learning in Deep Continuous-Time Recurrent Networks
BibTeX
@misc{gutlin2026local,
title = {{Local learning is all you need: brain-aligned predictive coding networks}},
author = {Dirk Gütlin and Ryszard Auksztulewicz and Adrien Doerig},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.37327},
eprint = {2610.37327},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.37327},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Local learning is all you need: brain-aligned predictive coding networks
AU - Dirk Gütlin
AU - Ryszard Auksztulewicz
AU - Adrien Doerig
PY - 2026
DA - 2026/10/27
PB - arXiv
DO - 10.48550/arxiv.2610.37327
UR - https://arxiv.org/abs/2610.37327
AB - Predictive Coding (PC) is an influential account of how brain representations emerge through hierarchical, local, self-supervised prediction-based learning, without requiring globally propagated error signals. Despite extensive evidence supporting PC, a striking paradox persists: computational models built on these biologically grounded principles have consistently failed to match state-of-the-art Deep Neural Networks in performance and brain-alignment. Here, we show that this paradox can be overcome. We introduce Predictive Brain Networks (PBNs), a hierarchical recurrent framework that implements local PC-based learning and achieves representational alignment with the human ventral visual stream matching or exceeding established vision models. Importantly, PBN top-down predictions encode unique, brain-aligned information not captured during bottom-up feature extraction, with this contribution increasing in locally trained variants. Further, PBNs substantially outperform existing PC-inspired networks on downstream classification tasks, reproduce key signatures of PC (with higher-level predictions shaping lower-level visual responses as observed in the primate cortex), and support uncertainty estimation. PBNs therefore close a longstanding gap in computational neuroscience by combining two properties that have been largely separated: the brain-inspired learning mechanisms of predictive coding and the representational power of modern deep networks. They provide a scalable framework for studying biologically grounded learning without sacrificing the capacity to produce rich neural representations.
ER -