Russell, there's a lot of recent work on supervised ML (including DL) for NLP text ... not so much on ML for program code... the NLP stuff is pretty specialized to the NLP context...
On Sun, Jan 24, 2016 at 3:30 AM, Russell Wallace <russell.wall...@gmail.com> wrote: > What's the current state-of-the-art in machine learning on complex data? > > To clarify what I mean: most machine learning algorithms assume you're > dealing with a small set of scalar variables. > > There have been good results from e.g. tiled neural networks for image > processing, where, very roughly speaking, you train a network to operate on > a small group of adjacent pixels and then tile it across the image. (This > has to be more or less how animal brains process vision.) > > But for data which is neither scalar nor straightforwardly tiled, like > program code or natural language text? It's been a good while since I > looked into the state-of-the-art in machine learning; where are things at > nowadays with that kind of data? > *AGI* | Archives <https://www.listbox.com/member/archive/303/=now> > <https://www.listbox.com/member/archive/rss/303/212726-deec6279> | Modify > <https://www.listbox.com/member/?&;> > Your Subscription <http://www.listbox.com> > -- Ben Goertzel, PhD http://goertzel.org "The reasonable man adapts himself to the world: the unreasonable one persists in trying to adapt the world to himself. Therefore all progress depends on the unreasonable man." -- George Bernard Shaw ------------------------------------------- AGI Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424 Modify Your Subscription: https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657 Powered by Listbox: http://www.listbox.com
