That was a great conference. I'm still kind of buzzed. My ideas are partially identical to everybody else's with a few exceptions.
On Mon, Oct 18, 2021 at 12:18 PM Jim Bromer <[email protected]> wrote: > > I am really enjoying listening to AGI-21 presentations. I liked Ben's > presentation and I learned something from it although I can't remember most > of it off hand. I also got something about the discussion about databases > even though that is more of a user-group thing. But I find myself heartily > approving much of what Linas is saying. First of all I agree about his 2013 > ideas about hypergraphs (which Ben mentioned) but I am concerned because > there isn't even a hint of a fantasy of fail-safe in that. (DBT: Dragons Be > There.) But if you are going to rely on graph theory than hypergraphs seem > like a necessity for general intelligence that is capable of reflection and > understanding. > But Linas's presentation on INLP is really interesting to me because I have > been thinking about something I call Artificial Artificial Neural Networks > and Linas had some ideas that could be relevant to what I would like to do. > (I have only thought about it and I do not see myself getting much of > anything done because my life of luxury is quickly coming to an end.) For > instance his normalization technique to find Similarity Scores is > interesting. I have thought about things like that but never tried anything. > I probably do not understand some of it but I am in the ballpark. I did > notice that he hasn't demonstrated that his Explainable Patterns INLP really > would work in more complicated situations but it is an important step to try > something like he did try. > > I am so glad that someone is capable of thinking outside the box. > > As I have been watching the presentations I have wondered if highly developed > abstractions are really necessary for advancing toward AGI. (I think > abstractions of 'expression' are necessary but I have wondered about > developed graph theory or logic or developed probability theory and so on). > There was another reason I wondered about highly developed abstraction > theories. They are amazing in mathematics but, as I have repeatedly > mentioned, computational arithmetic is effective because the n-ary or base n > representations of numbers where n>1 is an effective compression of the 1-ary > representation (ie making a mark for each item that is being counted.) And > then, the higher n-ary representations can be used in computational > arithmetic without being decompressed. It's amazing and it is the reason that > math is so important in science and things like computers. > But when you use abstractions for AI you do not have the spectacular > compression of (a general) representation of objects and of compression of > functions on those objects. So are highly developed abstractions for AGI > really going to be that useful? One thing I did not like about old-fashioned > probability reasoning was that the probability resultants lose the > association with their relevant sources of input. For a simple example, if we > want to try various what-if cases then the sources have to be found and > reimplemented. Yes they can be implemented but then the efficiency of the > system would be lost. > But I found an answer to my question: abstract representations might be > useful when the abstractions refer to reasoning itself (rather than just the > 'factoid' 'objects' of reasoning.) If an abstract form refers to some > reasoning, then not only could it be used to represent the generalization of > the reasoning, but it could also be used to implement a tool to rapidly try > various what-if scenarios without needing to go through endless "what was I > thinking" unraveling's. > > Artificial General Intelligence List / AGI / see discussions + participants + > delivery options Permalink ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tfda5d18b820b40ec-M592876f2937a1b80f794f340 Delivery options: https://agi.topicbox.com/groups/agi/subscription
