> I have also an idea about using evolutionary programming for training > combined Atomese/DNN models (e.g. for SynerGAN-ish models or VQA)...
Ah, interesting. Yes, an advantage of evolutionary algorithms is that they apply to basically any data type, or any combination thereof, etc. .. They are roughly equally mediocre for a wide variety of data types and fitness functions ;) ben On Wed, May 23, 2018 at 4:26 AM, Alexey Potapov <pota...@aideus.com> wrote: > Hi Ben, > >> >> I think it's better, if possible, to figure out a way to suitably >> modify the core PM rather than using a separate repo ... >> >> However, I guess the PM tweaks would need to be done someone on your team, >> as >> Linas and Nil probably are too busy and we don't have a lot of others >> who can rapidly perform such changes... >> >> I would personally be in favor of overloading stuff like TimesLink in >> order to apply to both >> NumberNodes and Values, because it seems to me that the Atom/Value >> distinction is more of >> an efficiency-driven implementation distinction rather than a >> fundamental mathematical/conceptual distinction... >> >> Nil and Linas should be consulted on this stuff, but at this point you >> are also in the exalted >> "inner circle" with foundational input on these OpenCog-architecture >> issues... > > > Got this. > >> >> >> If needed we could also introduce some sort of entity that is between >> a Value and an Atom in some sense -- i.e. we could introduce some sort of >> TensorValue entity that >> >> 1) Perhaps, knows what links to it (like an Atom but unlike a Value) >> >> 2) has an internal tensor that is mutable >> >> There is nothing prohibiting one from building something like this >> into Atomspace, >> though obviously not breaking various mechanisms would require some >> care... > > > OK, we will think about this. > >> >> > >> > Exactly. Probabilistic logic is a way to make inference over >> > probabilistic >> > programs much more efficient. I have specific examples for this in mind. >> >> It will be good to hear the examples when you have time... > > > Sure. I'm traveling now, and I'll have a talk on a conference soon. After > this, I will have time to go into detail > >> >> >> For instance, I like to think about evolutionary programming (e.g. >> MOSES) as a tool for learning procedural knowledge, but OTOH our main >> use of this tool right now is for learning classification rules. Now >> a program embodying a classification rule is, in a sense, a "procedure >> for performing the classification" ... but then in this sense, every >> logical inference is also a cognitive procedure ;p > > > I have also an idea about using evolutionary programming for training > combined Atomese/DNN models (e.g. for SynerGAN-ish models or VQA)... > > -- Alexey > > -- > You received this message because you are subscribed to the Google Groups > "opencog" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to opencog+unsubscr...@googlegroups.com. > To post to this group, send email to opencog@googlegroups.com. > Visit this group at https://groups.google.com/group/opencog. > To view this discussion on the web visit > https://groups.google.com/d/msgid/opencog/CABpRrhzQdwWp-gPQ6mGEjyF6WJpax1ya0MJePgQD6scZbk6aYQ%40mail.gmail.com. > > For more options, visit https://groups.google.com/d/optout. -- Ben Goertzel, PhD http://goertzel.org "Only those who will risk going too far can possibly find out how far they can go." - T.S. Eliot -- You received this message because you are subscribed to the Google Groups "opencog" group. To unsubscribe from this group and stop receiving emails from it, send an email to opencog+unsubscr...@googlegroups.com. To post to this group, send email to opencog@googlegroups.com. Visit this group at https://groups.google.com/group/opencog. To view this discussion on the web visit https://groups.google.com/d/msgid/opencog/CACYTDBfyCCvGs7oxo6nWFK_Dkcaaz7qLKvroJkQ2dYtdyfOAkg%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
