I go with it more as the semantics are general mathematical operators that instantiate their operational relationships situationally. Example, the AGI is observing a local entity the situational sematic operators resolve and coalesce inductively and deductively with a reflective complexity generated from a decided temporal expense. Other local sematic operators are resolved from other situations. Correlations and reuse of these operators across situations result in efficiencies which are aligned with learning and form a natural language semantic. The syntactics form from dimensionally projecting the semantics into an environment of particular Communication Complexity (Yao) characteristic. But the precise algebraic structure of the all those operators, both local and global, and glocal, comes up as, some sort of network... an octonionic structured network maybe? :)
John From: YKY (Yan King Yin, 甄景贤) via AGI [mailto:[email protected]] Sent: Thursday, June 19, 2014 4:57 PM To: AGI Subject: Re: [agi] Re: [GI] A question about tensor product On Thu, Jun 19, 2014 at 3:44 AM, Juan Carlos Kuri Pinto via AGI <[email protected] <mailto:[email protected]> > wrote: I would not use any mathematical tool unless it perfectly fits the problem to solve. I doubt tensor products can solve NLP. But I can be wrong. I would rather use analogical correspondences via Markov models for NLP. But I can be wrong too. :) If you model things as Markov chains of probabilities then you're really doing NLP and purely syntactically. But I think a more effective approach is to ignore the whims and irregularities of natural language and model "pure semantics" instead. That is the essence of a logic engine. We just need to find out the algebraic form of the semantics. The vectors / tensors can be seen as representations of the algebraic structure. ------------------------------------------- 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
