New Possibilities Using Trainable Digital Logic

Hello,

I thought I would share this informaton with the group and start a new
topic. I came across this information the other day regarding neural
networks and the applications in electronic design. Take a look below.

A long time goal of artificial intelligence (AI) is the development of
methods that can learn from examples to recognize events and make
decisions. For example, automatic recognition of speech is already in
widespread use, although this technology is far from usable in ordinary
conversations. Another example is the recognition of handwriting; here
the technology is still primitive. The eventual wide-spread consumer
use of decision making machines and robotics will depend on the
development of powerful, inexpensive, trainable devices which will
allow the evolution towards thinking machines with capabilities far in
excess of today's speech processors and robots.

NSC was founded to exploit a trainable high-speed technology called
trainable digital logic (TDL) that is inexpensive to implement for
recognition and decision making. TDL could form a basis for widespread
use of broader AI technology.

Consider a digital device that performs recognition and outputs a yes
or a no when the input is a digital word. For example, the input might
be numbers that are parameters characterizing an electrocardiogram
(ECG) beat, and the device must decide if the beat is a dangerous
arrhythmia.

When a sequence of bits is input to a logic circuit, which then outputs
a 1 or a 0, (e.g., answers yes or no), the circuit is called a
switching function. All digitally implemented pattern recognizers (such
as neural networks) that have a binary output are, in fact, switching
functions.

The word "trainable" means that examples of known categories (e.g.,
both dangerous and normal ECG beats) and a training algorithm can be
used to organize the device. The trained device will give the correct
answer (classification) when presented with examples where the category
is not known.

A key to NSC's technology is the development of efficient training
algorithms that can organize binary logic into complex switching
functions by using only binary inputs from known categories. The number
of categories need not be restricted to two; NSC has constructed logic
for up to sixteen categories.

I didn't want to put the full article here, so to read the full
technology - you can find it here: http://www.neuralsyscorp.com

.

Relevant Pages

  • Re: New Possibilities Using Trainable Digital Logic
    ... >I thought I would share this informaton with the group and start a new ... Another example is the recognition of handwriting; ... >the technology is still primitive. ... >as neural networks) that have a binary output are, in fact, switching ...
    (sci.electronics.design)
  • Mesh Networks: New Options for Wireless Users
    ... The race has begun to make wireless networks more viable for cities, ... environments where the technology used in today's Wi-Fi hotspots might ... Mesh Backbone ...
    (comp.dcom.telecom)
  • Re: How to get into Scientific Programming
    ... >> new principle or process. ... >mainly about technology, how technological knowledge accumulates, and ... That's what happened with the networks you see today. ... Compuserve sold access back then. ...
    (comp.programming)
  • Wireless Carriers Create 4G Initiative
    ... technology evolution beyond 3G." ... which calls itself the Next Generation Mobile Networks ... Initiative and which formally incorporated in the U.K. as NGMN ...
    (alt.internet.wireless)
  • Re: Evidence for Big Leaps?
    ... The biochemical networks and the networks of neurons ... networks even bother to create the mutations to produce nervous ... Therefore, after the multi-cellular technology was developed, ... networks in molecular level engineering of the new cells. ...
    (talk.origins)