AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Associative Memories via Predictive Coding

Tommaso Salvatori, Yuhang Song, Yujian Hong, Lei Sha, Simon Frieder, Zhenghua Xu, Rafal Bogacz, Thomas Lukasiewicz

NeurIPS 2021 · Architectures and efficiency › RNNs and normalization · approach: Hebbian and predictive coding · 31 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Increase depth to 10 layers (ablation)generative PCN · Tiny ImageNet 500 images, half pixelsimages reconstructed: more than 98%Improved
Replace autoencoder with generative PCN trained by predictive codingassociative memory · Tiny ImageNet 500 images, half pixelsimages reconstructed (%): 72% -> 98%Improved
Replace autoencoder with generative PCNassociative memory · Tiny ImageNet 500 images, 1/4 pixelsimages reconstructed (%): 48% -> 74%Improved
Replace modern Hopfield network with generative PCNassociative memory · CIFAR10 image retrievalimages retrieved: MHN at most 9 corrupted, 5 incompleteImproved
Increase depth of PCN (ablation)generative PCN · Flickr30k image-from-captionimages recoveredImproved
Increase width of PCN layers (ablation)generative PCN · Flickr30k caption/image recoveryrecovered countNo clear effect
Increase stored images from 50 to 500 (ablation)shallow generative PCN · Tiny ImageNet partial reconstructionimages reconstructedHurt
Reduce provided pixel fraction (ablation)generative PCN · Tiny ImageNet partial reconstructionimages reconstructedHurt
Store each image multiple times (3N, 5N) in MHN (ablation)Modern Hopfield Network · CIFAR10 retrievalimages retrieved: 5 -> 4 (N vs 5N, 50 images, 1/2 pixels)No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy