RE: COMP/AI: Advanced neural net

Crosby_M (
Mon, 6 Jan 1997 16:23:08 -0500

Max More forwarded an article on neural net technology:
<Dr. Sutherland, president of AND Corp., has created a new type of
computing that he calls holographic neural technology, and some of the
people using the new technology say its implications are staggering,
perhaps even frightening.>

The following was found on AltaVista but Netscape finds no DNS entry
for the URL:
<HNet Professional - $5000 (US) Allows the user to build
multi-cellular assemblies comprised of Holographic Neural Cells using
a Dynamic Link Library. This. - size 3K - 3 Dec 96>

The following was also found and extracted from

<AND Corporation of Hamilton, Ontario has developed a novel approach
to neural modeling very different from conventional techniques.
Instead of training a network by feeding one set of I/O data at a
time, all data is analysed together to produce an I/O map that
directly links input and output data. The method is not a
connectionist model. Instead, complex number arithmetic is used to
perform regression analysis. The phase angle represents the actual
value of the item, while the amplitude of the vector represents its
Degree of Belief.26

Holographic systems27 require only single cells to learn
stimulus-response associations. These systems can actually learn in
real time unlike connectionist models which require considerable time
to learn an I/O map. Holographic nets map all input/output data on one
pass directly into the structure of the neuron "cell". Speed of
learning is orders-of-magnitude greater than existing back-propagation

Holography is not simply retrieval of patterns. All I/O patterns are
actually superimposed onto the same set of synapses. The model has the
advantage of conventional network accuracy but at only a fraction of
the memory and processing time to perform a similar pattern-ID task.
HNet generalizes by performing interpolation among the trained I/O
mappings much as occurs in a Fuzzy Logic controller. Similar to the
numerous Defuzzification and Inferencing options available,
holographic networks allow a User to modify the generalization
characteristics so that mappings overlap as interpolation is
performed.26 >

Mark Crosby