Unsupervised predictive coding models may explain visual brain representation
This work addresses the problem of understanding brain representation in neuroscience by showing incremental improvements in predicting visual cortex activity using unsupervised models.
The paper investigates whether unsupervised predictive coding models can better predict visual brain activity than supervised image classification baselines, finding that their model outperforms these baselines with average noise normalized scores of 16.67% on fMRI and 27.67% on MEG tracks.
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.