# Deep Predictive Coding Network for Object Recognition

arXiv: https://arxiv.org/abs/1802.04762 · HTML: https://mlsanity.com/paper/1802.04762/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Feb 2018.

## Built on by (most cited first, 23 of 23)

- [Predictive Coding: a Theoretical and Experimental Review](https://mlsanity.com/paper/2107.12979/) (2021)
- [Self-Supervised Predictive Learning: A Negative-Free Method for Sound Source Localization in Visual Scenes](https://mlsanity.com/paper/2203.13412/) (2022)
- [Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics](https://mlsanity.com/paper/2106.02749/) (2021)
- [Brain-Inspired Machine Intelligence: A Survey of Neurobiologically-Plausible Credit Assignment](https://mlsanity.com/paper/2312.09257/) (2023)
- [Predictive coding feedback results in perceived illusory contours in a recurrent neural network](https://mlsanity.com/paper/2102.01955/) (2021)
- [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)
- [Using Human Perception to Regularize Transfer Learning](https://mlsanity.com/paper/2211.07885/) (2022)
- [Top-Down Guidance for Learning Object-Centric Representations](https://mlsanity.com/paper/2405.10598/) (2024)
- [Enhancing Sound Source Localization via False Negative Elimination](https://mlsanity.com/paper/2408.16448/) (2024)
- [On the role of feedback in visual processing: a predictive coding perspective](https://mlsanity.com/paper/2106.04225/) (2021)
- [Cognitive Coding of Speech](https://mlsanity.com/paper/2110.04241/) (2021)
- [Visually-Guided Sound Source Separation with Audio-Visual Predictive Coding](https://mlsanity.com/paper/2306.10684/) (2023)
- [Brain-like Flexible Visual Inference by Harnessing Feedback-Feedforward Alignment](https://mlsanity.com/paper/2310.20599/) (2023)
- [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)
- [Gradient Mask: Lateral Inhibition Mechanism Improves Performance in Artificial Neural Networks](https://mlsanity.com/paper/2208.06918/) (2022)
- [Deep Predictive Coding with Bi-directional Propagation for Classification and Reconstruction](https://mlsanity.com/paper/2305.18472/) (2023)
- [Early Exiting Predictive Coding Neural Networks for Edge AI](https://mlsanity.com/paper/2309.02022/) (2023)
- [Fast Deep Predictive Coding Networks for Videos Feature Extraction without Labels](https://mlsanity.com/paper/2409.04945/) (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)

Based on the predictive coding theory in neuroscience, we designed a bi-directional and recurrent neural net, namely deep predictive coding networks (PCN). It has feedforward, feedback, and recurrent connections. Feedback connections from a higher layer carry the prediction of its lower-layer representation; feedforward connections carry the prediction errors to its higher-layer. Given image input, PCN runs recursive cycles of bottom-up and top-down computation to update its internal representations and reduce the difference between bottom-up input and top-down prediction at every layer. After multiple cycles of recursive updating, the representation is used for image classification. With benchmark data (CIFAR-10/100, SVHN, and MNIST), PCN was found to always outperform its feedforward-only counterpart: a model without any mechanism for recurrent dynamics. Its performance tended to improve given more cycles of computation over time. In short, PCN reuses a single architecture to recursively run bottom-up and top-down processes. As a dynamical system, PCN can be unfolded to a feedforward model that becomes deeper and deeper over time, while refining it representation towards more accurate and definitive object recognition.