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

2 code implementations • NeurIPS 2021 • Bhavin Choksi, Milad Mozafari, Callum Biggs O'May, Benjamin Ador, Andrea Alamia, Rufin VanRullen

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.

Image Classification

Predictive coding feedback results in perceived illusory contours in a recurrent neural network

2 code implementations • NeurIPS Workshop SVRHM 2020 • Zhaoyang Pang, Callum Biggs O'May, Bhavin Choksi, Rufin VanRullen

Finally we validated our conclusions in a deeper network (VGG): adding the same predictive coding feedback dynamics again leads to the perception of illusory contours.

Brain-inspired predictive coding dynamics improve the robustness of deep neural networks

1 code implementation • NeurIPS Workshop SVRHM 2020 • Bhavin Choksi, Milad Mozafari, Callum Biggs O'May, B. ADOR, Andrea Alamia, Rufin VanRullen

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.

Image Classification