Could be deep neural networks, could also be constructivist symbolic neural net or hypothesis driven constructive induction (e.g. AQ17), or other induction methods (e.g., the Cruncher, or Ubercruncher). At this point I don't see any difference between a sign and a synthesized internal concept. ~PM.
From: naoya.arak...@nifty.com Subject: Re: [agi] Semiosis Date: Sun, 7 Apr 2013 10:30:23 +0900 To: a...@listbox.com Dear PM, I have a clarification question. With 1 (b), do you mean concept forming from scratch such as http://nyti.ms/T5E71eor forming 'occurrent' internal representation of concepts/signs? (Non natural) signs are conventionally (socially) formed and may or may not correspond to concepts formed with unsupervised learning… -- Naoya ARAKAWA On 2013/04/07, at 10:07, Piaget Modeler <piagetmode...@hotmail.com> wrote: Symbolic interactionism looks interesting. So, the beginnings of the AGI's semiosis components: `1. Decoder component (a) receives percepts, (b) forms concepts (i.e., signs), (c) matches or constructs ???? what ???? 2. Encoder component (a) starts with a semantic net (b) decides upon a subset of the semantic net to encode (c) chooses signs related to the concepts in the subset (d) forms a plan to utter the signs (e) executes the plan Is this enough. What is the name of 1.(c) ? Kindly advise. ~PMAGI | Archives | Modify Your Subscription AGI | Archives | Modify Your Subscription ------------------------------------------- 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
