[Date Prev][Date Next][Thread Prev][Thread Next]   [Date Index] [Thread Index] [Author Index

Neural Networks



Hey Jamie and Judith,
 
    Interesting posts.  I studied neural networks for several years as opposed to what's now called Classical AI, which is I suppose that disembodied super-intelligence that you refer to sometimes Judith.  People who gravitate towards neural networks are, I agree, much more likely in my opinion to stumble upon hidden entailments.  Especially if they are simultaneously looking at studies of real brains and their functioning.  I know that I did.  I spent several years thinking that the classical AI guys were way off, still do.  Now I feel that even many neural network approaches are likely to also be off the mark.  Mind and body are inseparable.  I now feel that if the mind is to be understood then this will likely entail moving the object of study from mind to brain and body and then on to life and organism.  Convenient huh?
 
I "built" several neural networks (simulated) and ultimately came to the conclusion that, though the networks did in fact do something akin to learning, the networks themselves (as opposed to their synaptic weights) were unentailed.  How do we account for the "architecture" of any given network?  I also now believe that if learning (which seems to me must involve anticipation) is to be embodied in computational models that this absolute distinction between hardware and software will have to be circumvented.  Anybody got any ideas?
 
 
David