DeepAI AI Chat
Log In Sign Up

Neural Networks with Recurrent Generative Feedback

by   Yujia Huang, et al.

Neural networks are vulnerable to input perturbations such as additive noise and adversarial attacks. In contrast, human perception is much more robust to such perturbations. The Bayesian brain hypothesis states that human brains use an internal generative model to update the posterior beliefs of the sensory input. This mechanism can be interpreted as a form of self-consistency between the maximum a posteriori (MAP) estimation of the internal generative model and the external environmental. Inspired by this, we enforce consistency in neural networks by incorporating generative recurrent feedback. We instantiate it on convolutional neural networks (CNNs). The proposed framework, termed Convolutional Neural Networks with Feedback (CNN-F), introduces a generative feedback with latent variables into existing CNN architectures, making consistent predictions via alternating MAP inference under a Bayesian framework. CNN-F shows considerably better adversarial robustness over regular feedforward CNNs on standard benchmarks. In addition, With higher V4 and IT neural predictivity, CNN-F produces object representations closer to primate vision than conventional CNNs.


page 2

page 3

page 4

page 5

page 10

page 11

page 16

page 17


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

Deep neural networks excel at image classification, but their performanc...

The principles of adaptation in organisms and machines II: Thermodynamics of the Bayesian brain

This article reviews how organisms learn and recognize the world through...

Extreme Value Preserving Networks

Recent evidence shows that convolutional neural networks (CNNs) are bias...

Human Eyes Inspired Recurrent Neural Networks are More Robust Against Adversarial Noises

Compared to human vision, computer vision based on convolutional neural ...

Interactive Analysis of CNN Robustness

While convolutional neural networks (CNNs) have found wide adoption as s...

Robust Perception through Analysis by Synthesis

The intriguing susceptibility of deep neural networks to minimal input p...

Steerable Pyramid Transform Enables Robust Left Ventricle Quantification

Although multifarious variants of convolutional neural networks (CNNs) h...

Code Repositories


Using CNN-F to correct protein docking.

view repo