If predictive coding networks were allowed to freely adjust every parameter (both neural activities and weights), they would naturally settle to a zero energy state which would be trivial and not perform any meaningful computation, so in practical implementations and likely in the brain, certain neurons are clamped to specific values

causalpending

Speaker

Primary Presenter

Evidence Quote

Let's now put everything together and see how this framework operates as a complete system. If we allow the network to freely adjust every parameter, both neural activities and the weights, it would naturally settle to a zero energy state. However, this solution would be trivial and not perform any meaningful computation. In practical implementations of predictive coding and likely in the brain itself, certain neurons are kind of clamped to specific values.

Source

The Brain’s Learning Algorithm Isn’t BackpropagationArtem Kirsanov
Created: 8/12/2026, 6:30:20 PM

My Notes

Loading notes...