Optimal prediction with resource constraints using the information bottleneck
Fig 7
The ability of the information bottleneck Method to predict history-dependent stimuli.
(a) The prediction problem, using an extended history and a future. This problem is largely similar to the one set up for the SDDHO but the past and the future are larger composites of observations within a window of time t−t0: t, expressed as Xpast for the past and t + Δt: t + Δt + t0, expressed as Xfuture for the future. (b) Predictive information with lag Δt. (c) The maximum available predictive information saturates as a function of the historical information used t0.