no code implementations • 2 Dec 2021 • André Ofner, Sebastian Stober
The model suggested here optimises hierarchical and dynamical predictions of latent states.
no code implementations • 16 Nov 2021 • André Ofner, Sebastian Stober
We present PredProp, a method for optimization of weights and states in predictive coding networks (PCNs) based on the precision of propagated errors and neural activity.
3 code implementations • 14 Jun 2019 • Roshan Rane, Edit Szügyi, Vageesh Saxena, André Ofner, Sebastian Stober
We fill in the gap by evaluating PredNet both as an implementation of the predictive coding theory and as a self-supervised video prediction model using a challenging video action classification dataset.
no code implementations • 5 Oct 2018 • André Ofner, Sebastian Stober
To establish this, a machine learning part learns to integrate into human cognition by explaining away multi-modal sensory measurements from the environment and physiology simultaneously with the brain signal.