# Unsupervised predictive coding models may explain visual brain representation

Source: [Unsupervised predictive coding models may explain visual brain representation](<https://www.sota2.com/research/paper/68fa5ee81e209131ce9e627f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T19:03:51.947Z

Authors: Marcio Fonseca

Published: 2019-06-30T19:53:32.000Z

## Abstract

Deep predictive coding networks are neuroscience-inspired unsupervised learning models that learn to predict future sensory states. We build upon the PredNet implementation by Lotter, Kreiman, and Cox (2016) to investigate if predictive coding representations are useful to predict brain activity in the visual cortex. We use representational similarity analysis (RSA) to compare PredNet representations to functional magnetic resonance imaging (fMRI) and magnetoencephalography (MEG) data from the Algonauts Project. In contrast to previous findings in the literature (Khaligh-Razavi &Kriegeskorte, 2014), we report empirical data suggesting that unsupervised models trained to predict frames of videos may outperform supervised image classification baselines. Our best submission achieves an average noise normalized score of 16.67% and 27.67% on the fMRI and MEG tracks of the Algonauts Challenge.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1907.00441>)

[PDF](<https://arxiv.org/pdf/1907.00441.pdf>)