preprint · ArXiv.org · 2025
Bidirectional predictive coding
Gaspard Oliviers, Mufeng Tang, Rafał Bogacz
Cited by 1Open access
Abstract
Predictive coding (PC) is an influential computational model of visual learning and inference in the brain. Classical PC was proposed as a top-down generative model, where the brain actively predicts upcoming visual inputs, and inference minimises the prediction errors. Recent studies have also shown that PC can be formulated as a discriminative model, where sensory inputs predict neural activities in a feedforward manner. However, experimental evidence suggests that the brain employs both generative and discriminative inference, while unidirectional PC models show degraded performance in tasks requiring bidirectional processing. In this work, we propose bidirectional PC (bPC), a PC model that incorporates both generative and discriminative inference while maintaining a biologically plausible circuit implementation. We show that bPC matches or outperforms unidirectional models in their specialised generative or discriminative tasks, by developing an energy landscape that simultaneously suits both tasks. We also demonstrate bPC's superior performance in two biologically relevant tasks including multimodal learning and inference with missing information, suggesting that bPC resembles biological visual inference more closely.
Cite this paper
Oliviers, G., Tang, M., & Bogacz, R. (2025). Bidirectional predictive coding. ArXiv.org. https://doi.org/10.48550/arxiv.2505.23415
Oliviers, Gaspard, et al. “Bidirectional predictive coding.” ArXiv.org, 2025, https://doi.org/10.48550/arxiv.2505.23415.
Oliviers, Gaspard, Mufeng Tang, and Rafał Bogacz. 2025. “Bidirectional predictive coding.” ArXiv.org. https://doi.org/10.48550/arxiv.2505.23415.
Oliviers, G., Tang, M. and Bogacz, R. (2025) ‘Bidirectional predictive coding’, ArXiv.org. Available at: https://doi.org/10.48550/arxiv.2505.23415.
@misc{oliviers2025bidirectional,
title = {{Bidirectional predictive coding}},
author = {Oliviers, Gaspard and Tang, Mufeng and Bogacz, Rafał},
journal = {ArXiv.org},
year = {2025},
doi = {10.48550/arxiv.2505.23415}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.