Review for NeurIPS paper: Can the Brain Do Backpropagation? --- Exact Implementation of Backpropagation in Predictive Coding Networks

Following the author response, we had a long discussion. On the positive side, this is the first algorithm with local update rules that exactly simulates BP (at least asymptotically, given complete convergence at the initialization). On the negative side, all reviewers agreed this algorithm has some reduced plausibility. Specifically, in IL (original PCN) we have to present both input and output, and wait sufficient time until convergence. In contrast, in Z-IL and Fa-Z-IL, we have to first present (only) the input, also wait sufficient time until convergence, and then present the output; In addition, the learning rule becomes more complicated (through the introduction of the Phi function) and we must detect when "the change in error node is caused by feedback input" (which seems to require some global signals). This seems more complicated and less plausible then the original IL.