Here’s my fluffy perspective of this issue so far:
The algebraic structure are represented in graphs temporally and neutrosophicly. The atoms dynamically change, splitting and joining, based on input complexity flux with compression of input into local situational symbol groups. Symbols are generated and reflected dynamically from a complexity indexing of the input, discretely or analog continuous. The graph dynamically generates and degenerates atoms and learning is based on the algebraic structure complexity derived from the situational algebraic structure complexity of input. The reaction/interaction of the graph structure to the input structure is where it gets interesting. I see everything as symbols, infinite symbols indexed universally but they degenerate to finite/discrete locally which then thus can make languages or do whatever. I’m trying to focus the operational complexity in order to minimize number of connections. Whether or not it works in reality is another thing. I think that’s what we are talking about... ? Maybe.. Those are good interesting papers you referenced. Ben’s is quite an awesome paper too. I sort of have to slowly arrive at my own view/invention for stuff like this so that I can understand it more, recreating the wheel sometimes, but I look at others work for inspiration. Even though I don’t fully understand yet the method in Ben’s paper, I randomly sample it visually, I read it back and forth just a few words at a time, never more than one or two sentences in a row, with other papers and books too. It’s aesthetics I think? Whole papers are really symbols, one paper is a symbol on a universal index of symbols and it can be compressed or decompressed and you also can view it initially in a compressed state I guess.. like an FFT or something? An then they can be cross-correlated so our whole species as a multi-agent intelligence is populating regions of the universal index... John From: YKY (Yan King Yin, 甄景贤) [mailto:[email protected]] Sent: Wednesday, February 5, 2014 2:15 PM To: AGI Subject: Re: [agi] Ben's geometry of mind paper On Fri, Jan 31, 2014 at 6:59 PM, John Rose <[email protected]> wrote: Not sure if this is what you are asking but ?Cmaybe you could use NCM’s (Neutrospohic Cognitive Maps) with a neutrosphic adjacency matrix? That might eliminate discrete “jumps”…. John Thanks, I will have a look at the NCM thesis. What I'm trying to do is similar to neural-symbolic integration, but my scope is broader, in the sense that I would consider any spatial technique, not just neural. I have looked at a number of neural-symbolic proposals, but they don't seem to be particularly efficient. So they proved that it is feasible, but they're still far from practical. However, I am particularly impressed with the following: 1. Paul Smolensky's "Tensor product variable binding and the representation of symbolic structures in connectionist systems" (1990). (I think Ben recommended this one to me...) It's capable of representing Lisp-like trees using neural networks, via vector sums and tensor products. This is very close to my idea of using algebraic sums and products to represent logic formula trees. I'm still trying to understand Smolensky's use of tensor products. His book "The harmonic mind" (2006) may be easier to read. 2. "Parsing Natural Scenes and Natural Language with Recursive Neural Networks" Socher, Lin, Ng, Manning (2011) is also very impressive. They're able to use a hybrid neural-tree structure to learn to parse natural language sentences and visual scenes. Note: their ANN is "recursive" but not "recurrent", it's actually feed-forward. It's very inspiring because parsing is a process that can require a logic engine, and yet they're able to use a neural network to perform the same function... I'm trying to see where exactly the 'cheating' is taking place.... =) Logic is slow; my purpose is to replace the logic engine with something faster (but approximate), and yet not losing the universal expressive power of logic. AGI | <https://www.listbox.com/member/archive/303/=now> Archives <https://www.listbox.com/member/archive/rss/303/248029-3b178a58> https://www.listbox.com/images/feed-icon-10x10.jpg| <https://www.listbox.com/member/?&;> Modify Your Subscription <http://www.listbox.com/> https://www.listbox.com/images/listbox-logo-small.png ------------------------------------------- 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
<<image001.jpg>>
<<image002.png>>
