Greetings! What would it take to design a Neural Fuzzy Ontological Expert System? For example, for an application in Data Mining or Pattern Recognition? TTH (Rexsy) Rexsy.com <>*<> [ comp.ai is moderated ... your article may take a while to appear. ]
<> Neural Ontological Expert System <>
Started by ●June 10, 2008
Reply by ●June 10, 20082008-06-10
(reply list trimmed to comp.ai and comp.dsp) Dr. Tuan T. Ho wrote:> Greetings! > > What would it take to design a Neural Fuzzy Ontological Expert > System? For example, for an application in Data Mining or Pattern > Recognition? > > TTH (Rexsy) > Rexsy.com > > <>*<> >A room full of buzzwords, apparently. This is not an application that I would associate with DSP, unless you are using DSP processors in an attempt to make a neural net execute at useful speeds. -- Tim Wescott Wescott Design Services http://www.wescottdesign.com Do you need to implement control loops in software? "Applied Control Theory for Embedded Systems" gives you just what it says. See details at http://www.wescottdesign.com/actfes/actfes.html [ comp.ai is moderated ... your article may take a while to appear. ]
Reply by ●June 11, 20082008-06-11
Dr. Tuan T. Ho wrote:> Greetings! > > What would it take to design a Neural Fuzzy Ontological Expert > System? For example, for an application in Data Mining or Pattern > Recognition?It would take the surge, the misunderestimate, the turbo coding, the wavelets, the gradual improvement, the strategic marketing focus and many other meaningless stock phrases. It is what it is. Vladimir Vassilevsky DSP and Mixed Signal Design Consultant http://www.abvolt.com [ comp.ai is moderated ... your article may take a while to appear. ]
Reply by ●June 11, 20082008-06-11
On Jun 10, 8:06 am, "Dr. Tuan T. Ho" <Tuan.Thanh...@gmail.com> wrote:> Greetings! > > What would it take to design a Neural Fuzzy Ontological Expert > System? For example, for an application in Data Mining or Pattern > Recognition? > > TTH (Rexsy) > Rexsy.com > > <>*<> >Some of those words seem to be orthogonal (in the way I understand them) to each other. When I see "Expert System", I hear "giant if-then-else" When I see "Neural Network", I hear "Machine Learning", supervised or unsupervised. As you may imagine, actual Machine learning could not be further from handcoded logic like if-then-else is. I'm not saying it doesn't make sense, just struggling to understand the problem domain. So, the question to ask is, why do you want to combine those different approaches? What specific problem(s) do you want to solve that need a combination of fuzzy logic, neural network, and handcoded if-then-else loops. Best Regards, Milind [ comp.ai is moderated ... your article may take a while to appear. ]
Reply by ●June 12, 20082008-06-12
"Dr. Tuan T. Ho" <Tuan.Thanh...@gmail.com> wrote:> What would it take to design a Neural Fuzzy > Ontological Expert System? For example, for an > application in Data Mining or Pattern Recognition?> TTH (Rexsy) > Rexsy.comWell, the general idea seems to have been addressed at least a few times, maybe these hits will help: http://www.google.com/search?q=neural.net+ontological.system+%28data.mining+OR+pattern.recognition%29 xanthian
Reply by ●June 13, 20082008-06-13
On Jun 11, 10:58�pm, Kent Paul Dolan <xanth...@well.com> wrote:> "Dr. Tuan T. Ho" <Tuan.Thanh...@gmail.com> wrote: > > > What would it take to design a Neural Fuzzy > > Ontological Expert System? �For example, for an > > application in Data Mining or Pattern Recognition? > > TTH (Rexsy) > > Rexsy.com > > Well, the general idea seems to have been addressed > at least a few times, maybe these hits will help: > > http://www.google.com/search?q=neural.net+ontological.system+%28data.... > > xanthianThere are some interesting ideas there! As you can see, this is relatively new...there are not too many results out there yet..Thx. Rexsy (TTH) Rexsy.com
Reply by ●June 13, 20082008-06-13
On Jun 10, 6:14�pm, Tim Wescott <t...@seemywebsite.com> wrote:> (reply list trimmed to comp.ai and comp.dsp) > > Dr. Tuan T. Ho wrote: > > > Greetings! > > > What would it take to design a Neural Fuzzy Ontological Expert > > System? �For example, for an application in Data Mining or Pattern > > Recognition? > > > TTH (Rexsy) > > Rexsy.com > > > <>*<> > > A room full of buzzwords, apparently. > > This is not an application that I would associate with DSP, unless you > are using DSP processors in an attempt to make a neural net execute at > useful speeds. > > -- > > Tim Wescott > Wescott Design Serviceshttp://www.wescottdesign.com > > Do you need to implement control loops in software? > "Applied Control Theory for Embedded Systems" gives you just what it says. > See details athttp://www.wescottdesign.com/actfes/actfes.html > > [ comp.ai is moderated ... your article may take a while to appear. ]Yes, using the DSP processors to implement the neural networks at useful speeds. Of course, with the fuzzy logic algorithm embedded in the NN architecture, we would then have the Neural Fuzzy Expert System (NFES) on the DSP processors. Now, the question is, how would we go about inserting a simple ontological structure into the NFSE? Rexsy (TTH) Rexsy.com
Reply by ●June 13, 20082008-06-13
On Jun 11, 7:37�pm, Vladimir Vassilevsky <antispam_bo...@hotmail.com> wrote:> Dr. Tuan T. Ho wrote: > > > Greetings! > > > What would it take to design a Neural Fuzzy Ontological Expert > > System? �For example, for an application in Data Mining or Pattern > > Recognition? > > It would take the surge, the misunderestimate, the turbo coding, the > wavelets, the gradual improvement, the strategic marketing focus and > many other meaningless stock phrases. It is what it is. > > Vladimir Vassilevsky > DSP and Mixed Signal Design Consultanthttp://www.abvolt.com > > [ comp.ai is moderated ... your article may take a while to appear. ]Yes, certainly! It is what it is! Welcome the real world! Rexsy Rexsy.com
Reply by ●June 13, 20082008-06-13
On Jun 11, 7:38�pm, Milind Joshi <milind.a.jo...@gmail.com> wrote:> On Jun 10, 8:06 am, "Dr. Tuan T. Ho" <Tuan.Thanh...@gmail.com> wrote: > > > Greetings! > > > What would it take to design a Neural Fuzzy Ontological Expert > > System? �For example, for an application in Data Mining or Pattern > > Recognition? > > > TTH (Rexsy) > > Rexsy.com > > > <>*<> > > Some of those words seem to be orthogonal (in the way I understand > them) to each other.This is the real world...things appear to be orthogonal sometimes...> When I see "Expert System", I hear "giant if-then-else"That's part of it (knowledge-based intelligence), there's also the computational intelligence/expert system as well (e.g. Neural Expert System)> When I see "Neural Network", I hear "Machine Learning", supervised or > unsupervised.Yes...> As you may imagine, actual Machine learning could not be further from > handcoded logic like if-then-else is. > > I'm not saying it doesn't make sense, just struggling to understand > the problem domain. > > So, the question to ask is, why do you want to combine those different > approaches? > What specific problem(s) do you want to solve that need a combination > of fuzzy logic, neural network, and handcoded if-then-else loops.The idea is to combine both knowledge-based and computational intelligence into one brain, ontologically. Some of the real world problems are quite complex, and we do want to design smart machines the could mimic the human intelligent information processing and controls capabilities...> Best Regards, > Milind > > [ comp.ai is moderated ... your article may take a while to appear. ]Rexsy (TTH) Rexsy.com
Reply by ●June 16, 20082008-06-16
On Jun 10, 5:06 am, "Dr. Tuan T. Ho" <Tuan.Thanh...@gmail.com> wrote:> Greetings! > > What would it take to design a Neural Fuzzy Ontological Expert > System? For example, for an application in Data Mining or Pattern > Recognition? > > TTH (Rexsy) > Rexsy.com > > <>*<>That sounds cool, how do you plan to represent all the words and grammatical structure?
