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

Abstract

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.

arXiv commentPaper presented at NeurIPS 2021

References in corpus (24)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Densely Connected Convolutional Networks
• Adversarially Robust Generalization Requires More Data
• Recurrence is required to capture the representational dynamics of the human visual system
• Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
• MagNet: a Two-Pronged Defense against Adversarial Examples
• Foolbox: A Python toolbox to benchmark the robustness of machine learning models
• A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples
• Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
• The Robust Manifold Defense: Adversarial Training using Generative Models
• Brain-Like Object Recognition with High-Performing Shallow Recurrent ANNs
• APE-GAN: Adversarial Perturbation Elimination with GAN
• Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples
• Deep Predictive Coding Network for Object Recognition
• DARCCC: Detecting Adversaries by Reconstruction from Class Conditional Capsules
• Deep Predictive Coding Networks
• Neural Networks with Recurrent Generative Feedback
• Recurrent Connections Aid Occluded Object Recognition by Discounting Occluders
• Stable and expressive recurrent vision models
• Adversarial Robustness of Supervised Sparse Coding
• Improving the robustness of ImageNet classifiers using elements of human visual cognition

Cited by in corpus (3)

• Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learning
• Multimodal neural networks better explain multivoxel patterns in the hippocampus
• Mathematical derivation of wave propagation properties in hierarchical neural networks with predictive coding feedback dynamics