Predictive coding networks for temporal prediction
Fig 3
The tracking task and the impact of inference step size and the number of inference steps on performance.
A. The dynamics of the true hidden state are represented as a 3-dimensional vector at each time step, with entries corresponding to position (x1), velocity (x2) and acceleration (x3). B. The projected noisy observations from the true system state in A. C: Estimates of the acceleration with different models, zoomed in at the interval between 560 and 600 time steps. D: MSE difference between tPC and Kalman filter, with varying numbers of inference steps and step sizes for predictive coding. PC stands for temporal predictive coding and KF stands for Kalman filter. All values are with arbitrary units (a.u.).