Hacker News Reader

Deep Learning: The Rodneying.

Seriously though, I've been reading up on insect neurology over the last couple of weeks, and then looking at Boston Dynamics' new stuff, and wondering how much subsumption is mixed in with their traditional motion planning.

View on HN

Yeah leaving aside the (possibly warranted) cynical tone in GP... It seems to me that ensembles (and related structures, I'm playing fast and loose here) are the modern ML counterpart of subsumption.. driving an ensemble, MOE, etc with more complex supervisor models (especially reinforcement models) essentially gets us the Brooks architecture, but with less of a demand for explicit programming of individual behaviors. That demand is the part of Brook's vision that strikes me as unrealistic, especially for tasks like driving. Though of course everything was more optimistic in the 80s.

Reply on news.ycombinator.com