box; analysis of complexity; redesign and/or annotation for Figure 1; Figure 2A adaptation; and typo corrections

Chung et al., 2015; Fraccaro et al., 2017) represent states Fraccaro; or Johnson et al., 2016), but currently only implemented for R2: Encoding functions: indeed, we chose fixed but random γ . Gradient descent would be a natural choice, albeit with debatable biological plausibility. If accepted, we will include these new experimental results. Line 92: Indeed, DDC activities encode a distribution or belief about a random variable - we will amend the text. This could follow "normal" learning rules; with the DDC again ensuring that uncertainty is handled correctly.