Hybrid predictive coding: Inferring, fast and slow
Fig 2
Hybrid predictive coding combines two phases of inference as follows.
(A) At stimulus onset, data x is propagated up the hierarchy in a feedforward manner, utilising the amortised functions fϕ(⋅). These predictions set the initial conditions for μ, which parameterise posterior beliefs about the sensory data. These predictions are associated with error units that track the difference between variables at one level and the variables at the level above under transforms fϕ(⋅). These errors are not utilised for inference but are used to update the amortised parameters ϕ during learning (weight updates). (B) The initial values for μ are then used to predict the activity at the layer below, transformed by the generative functions fθ(⋅). These predictions incur prediction errors ε, which are then used to update beliefs μ. This process is repeated N times, after which perceptual inference is complete.