# Deep Predictive Coding Network with Local Recurrent Processing for Object Recognition

arXiv: https://arxiv.org/abs/1805.07526 · HTML: https://mlsanity.com/paper/1805.07526/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2018.

## Built on by (most cited first, 25 of 25)

- [Predictive Coding: Towards a Future of Deep Learning beyond Backpropagation?](https://mlsanity.com/paper/2202.09467/) (2022)
- [Brain-inspired Computational Intelligence via Predictive Coding](https://mlsanity.com/paper/2308.07870/) (2023)
- [Predictive Coding beyond Gaussian Distributions](https://mlsanity.com/paper/2211.03481/) (2022)
- [Convolutional Neural Generative Coding: Scaling Predictive Coding to Natural Images](https://mlsanity.com/paper/2211.12047/) (2022)
- [Spiking Neural Networks and Bio-Inspired Supervised Deep Learning: A Survey](https://mlsanity.com/paper/2307.16235/) (2023)
- [Predictive Coding Networks and Inference Learning: Tutorial and Survey](https://mlsanity.com/paper/2407.04117/) (2024)
- [Block-local learning with probabilistic latent representations](https://mlsanity.com/paper/2305.14974/) (2023)
- [Predictive Coding beyond Correlations](https://mlsanity.com/paper/2306.15479/) (2023)
- [Augmenting BERT-style Models with Predictive Coding to Improve Discourse-level Representations](https://mlsanity.com/paper/2109.04602/) (2021)
- [Active Sensing with Predictive Coding and Uncertainty Minimization](https://mlsanity.com/paper/2307.00668/) (2023)
- [Faster Convergence in Deep-Predictive-Coding Networks to Learn Deeper Representations](https://mlsanity.com/paper/2101.06848/) (2021)
- [Predictive coding, precision and natural gradients](https://mlsanity.com/paper/2111.06942/) (2021)
- [Classification and Reconstruction Processes in Deep Predictive Coding Networks: Antagonists or Allies?](https://mlsanity.com/paper/2401.09237/) (2024)
- [CogDPM: Diffusion Probabilistic Models via Cognitive Predictive Coding](https://mlsanity.com/paper/2405.02384/) (2024)
- [PhiNets: Brain-inspired Non-contrastive Learning Based on Temporal Prediction Hypothesis](https://mlsanity.com/paper/2405.14650/) (2024)
- [Gradient-adjusted Incremental Target Propagation Provides Effective Credit Assignment in Deep Neural Networks](https://mlsanity.com/paper/2102.11598/) (2021)
- [Difference-Driven Gating: Adaptive Feature Fusion for U-Net Decoder](https://mlsanity.com/paper/2607.11096/) (2026)
- [Spatio-Temporal Feedback Control of Small Target Motion Detection Visual System](https://mlsanity.com/paper/2211.10128/) (2022)
- [Early Exiting Predictive Coding Neural Networks for Edge AI](https://mlsanity.com/paper/2309.02022/) (2023)
- [Self-Attention-Based Contextual Modulation Improves Neural System Identification](https://mlsanity.com/paper/2406.07843/) (2024)
- [Fast Deep Predictive Coding Networks for Videos Feature Extraction without Labels](https://mlsanity.com/paper/2409.04945/) (2024)
- [Predictive Attractor Models](https://mlsanity.com/paper/2410.02430/) (2024)
- [DMPCN: Dynamic Modulated Predictive Coding Network with Hybrid Feedback Representations](https://mlsanity.com/paper/2504.14665/) (2025)
- [Sensory robustness through top-down feedback and neural stochasticity in recurrent vision models](https://mlsanity.com/paper/2508.07115/) (2025)
- [Predictive Coding-based Deep Neural Network Fine-tuning for Computationally Efficient Domain Adaptation](https://mlsanity.com/paper/2509.20269/) (2025)

## Abstract (arXiv)

Inspired by "predictive coding" - a theory in neuroscience, we develop a bi-directional and dynamic neural network with local recurrent processing, namely predictive coding network (PCN). Unlike feedforward-only convolutional neural networks, PCN includes both feedback connections, which carry top-down predictions, and feedforward connections, which carry bottom-up errors of prediction. Feedback and feedforward connections enable adjacent layers to interact locally and recurrently to refine representations towards minimization of layer-wise prediction errors. When unfolded over time, the recurrent processing gives rise to an increasingly deeper hierarchy of non-linear transformation, allowing a shallow network to dynamically extend itself into an arbitrarily deep network. We train and test PCN for image classification with SVHN, CIFAR and ImageNet datasets. Despite notably fewer layers and parameters, PCN achieves competitive performance compared to classical and state-of-the-art models. Further analysis shows that the internal representations in PCN converge over time and yield increasingly better accuracy in object recognition. Errors of top-down prediction also reveal visual saliency or bottom-up attention.