mlsanityData to 7 Oct 2026

Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics

arXiv 2106.02749 ↗First posted 4 Jun 2021cs.CV q-bio.NCcited by 19

Not on the map. Why?

Abstract (arXiv)

Deep neural networks excel at image classification, but their performance is far less robust to input perturbations than human perception. In this work we explore whether this shortcoming may be partly addressed by incorporating brain-inspired recurrent dynamics in deep convolutional networks. We take inspiration from a popular framework in neuroscience: 'predictive coding'. At each layer of the hierarchical model, generative feedback 'predicts' (i.e., reconstructs) the pattern of activity in the previous layer. The reconstruction errors are used to iteratively update the network's representations across timesteps, and to optimize the network's feedback weights over the natural image dataset-a form of unsupervised training. We show that implementing this strategy into two popular networks, VGG16 and EfficientNetB0, improves their robustness against various corruptions and adversarial attacks. We hypothesize that other feedforward networks could similarly benefit from the proposed framework. To promote research in this direction, we provide an open-sourced PyTorch-based package called Predify, which can be used to implement and investigate the impacts of the predictive coding dynamics in any convolutional neural network.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 36 of its 78 references that are in the map. First posted on arXiv 4 Jun 2021.

Builds on

36 of 78 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2013Intriguing properties of neural networkscited by 5,114
  8. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  9. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  10. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  11. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  12. 2018Adversarially Robust Generalization Requires More Datacited by 318
24 more
  1. 2018Feature Denoising for Improving Adversarial Robustnesscited by 312
  2. 2019Adversarial Examples Improve Image Recognitioncited by 283
  3. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 268
  4. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  5. 2016Deep Predictive Coding Networks for Video Prediction and Unsupervised Learningcited by 203
  6. 2018Learning long-range spatial dependencies with horizontal gated-recurrent unitscited by 98
  7. 2019Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Trainingcited by 95
  8. 2019Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNscited by 90
  9. 2019The Odds are Odd: A Statistical Test for Detecting Adversarial Examplescited by 75
  10. 2016A Boundary Tilting Persepective on the Phenomenon of Adversarial Examplescited by 70
  11. 2019Recurrence is required to capture the representational dynamics of the human visual systemcited by 58
  12. 2017APE-GAN: Adversarial Perturbation Elimination with GANcited by 57
  13. 2017Dense Associative Memory is Robust to Adversarial Inputscited by 45
  14. 2018Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samplescited by 38
  15. 2017The Robust Manifold Defense: Adversarial Training using Generative Modelscited by 35
  16. 2018Deep Predictive Coding Network for Object Recognitioncited by 23
  17. 2020Neural Networks with Recurrent Generative Feedbackcited by 23
  18. 2020Adversarial Robustness of Supervised Sparse Codingcited by 22
  19. 2020Stable and expressive recurrent vision modelscited by 20
  20. 2013Deep Predictive Coding Networkscited by 13
  21. 2021Predictive coding feedback results in perceived illusory contours in a recurrent neural networkcited by 10
  22. 2018DARCCC: Detecting Adversaries by Reconstruction from Class Conditional Capsulescited by 9
  23. 2019Recurrent Connections Aid Occluded Object Recognition by Discounting Occluderscited by 5
  24. 2019Improving the robustness of ImageNet classifiers using elements of human visual cognitioncited by 2

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 4; 2023: 4; 2024: 7; 2025: 2.

19 papers.

Sort:

By area:

  1. 2023Brain-inspired Computational Intelligence via Predictive Codingcited by 30
  2. 2022A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networkscited by 21
  3. 2022Convolutional Neural Generative Coding: Scaling Predictive Coding to Natural Imagescited by 10
  4. 2022Diversity vs. Recognizability: Human-like generalization in one-shot generative modelscited by 9
  5. 2024Predictive Coding Networks and Inference Learning: Tutorial and Surveycited by 7
  6. 2024Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learningcited by 4
  7. 2021Multimodal neural networks better explain multivoxel patterns in the hippocampuscited by 3
  8. 2024Latent Representation Matters: Human-like Sketches in One-shot Drawing Taskscited by 3
  9. 2021On the role of feedback in visual processing: a predictive coding perspectivecited by 2
  10. 2023Brain-like Flexible Visual Inference by Harnessing Feedback-Feedforward Alignmentcited by 2
  11. 2024pyhgf: A neural network library for predictive codingcited by 2
  12. 2022An overview of open source Deep Learning-based libraries for Neurosciencecited by 1
7 more
  1. 2024Limited but consistent gains in adversarial robustness by co-training object recognition models with human EEGcited by 1
  2. 2024Contextual Feedback Loops: Amplifying Deep Reasoning with Iterative Top-Down Feedbackcited by 1
  3. 2023Fixed Inter-Neuron Covariability Induces Adversarial Robustnesscited by 0
  4. 2023Early Exiting Predictive Coding Neural Networks for Edge AIcited by 0
  5. 2024How Robust Are Energy-Based Models Trained With Equilibrium Propagation?cited by 0
  6. 2025GASPnet: Global Agreement to Synchronize Phasescited by 0
  7. 2025Sensory robustness through top-down feedback and neural stochasticity in recurrent vision modelscited by 0