Everyone seems to want to compute with positives - indicators, probabilities, confidence, etc. HOWEVER, the math is more solid when computing with negatives, e.g. the likelihood that there is NO indicator of the absence of something. The presence/absence is often difficult to compute, but the indicators are easy to compute - and, lots of indicators of something is still unreliable, but an indicator of the absence of something is MUCH more reliable.
See what I mean - simpler math leading to quantitatively correct results? Steve On Wed, Jun 12, 2019, 9:18 AM Jim Bromer <[email protected]> wrote: > I watched the video on Binons but not the one on Hierarchies. I have been > at this for longer than I care to admit so I feel that I have seen things > like this before. I am looking forward to watching the video on > Hierarchies. My imagining of what I might be able to effectively use as a > kind of conceptual mathematics is not going to be answered by a nodal > network kind of thing - even though it would probably be accurately > described as a kind of nodal network. Does that make sense? If someone > talked about a nodal network I would think of something that was similar to > a neural network or a conceptual network. But, the thing is, that both > these networks are going to use conventional mathematical methods to > represent the weights of the system (or the discrete decision methods of > the system.) Now, even if I was able to successfully develop my idea of a > different kind of mathematics it still could be analyzed using traditional > or conventional computational methods. So it would probably be describable > using nodal networks along with conventional mathematics. But the point is > that maybe there is some kind of non-conventional mathematics that could be > useful and especially efficient in a specialized AI program, just because > the program is specialized and does not need to apply the broad range of > utilizations that conventional mathematics can reach. > I am interested in the video of the Hierarchies and I will watch it > tonight. > Jim Bromer > > > On Tue, Jun 11, 2019 at 10:05 PM Brett N Martensen <[email protected]> > wrote: > >> Hi Jim, I've been following this discussion with interest. Good stuff. >> If you are looking for a way of representing those millions of bits and >> only use a small part of it at a time and build it hierarchically may I >> suggest you look into binons. In the presentations on binons and the >> presentation on hierarchies (slide 13) it shows how to combine many >> independent properties/features using binary nodes. The website is >> www.adaptroninc.com Cheers, Brett >> > *Artificial General Intelligence List <https://agi.topicbox.com/latest>* > / AGI / see discussions <https://agi.topicbox.com/groups/agi> + > participants <https://agi.topicbox.com/groups/agi/members> + delivery > options <https://agi.topicbox.com/groups/agi/subscription> Permalink > <https://agi.topicbox.com/groups/agi/T395236743964cb4b-Mf6d50ab412c7d34484433422> > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T395236743964cb4b-Md22a5980d1685073d2386f39 Delivery options: https://agi.topicbox.com/groups/agi/subscription
