Is imitative generalization usually envisioned as a recursive many-iterations-process like IDA? Or is it just a single iteration of train the initial model → inspect and correct the priors → train the new model?
Great post, by the way.
Is imitative generalization usually envisioned as a recursive many-iterations-process like IDA? Or is it just a single iteration of train the initial model → inspect and correct the priors → train the new model?
Great post, by the way.