Devices for use in neural processing

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

395 22, G06F 1518

Patent

active

055531970

DESCRIPTION:

BRIEF SUMMARY
BACKGROUND OF THE INVENTION

This invention relates to artificial neuron-like devices (hereinafter referred to simply as "neurons") for use in neural processing.
One of the known ways of realising a neuron in practice is to use a random access memory (RAM). The use of RAMs for this purpose dates back a considerable number of years. It has been suggested that if one were able to construct a RAM in which a given output, say a `1`, was produced by a given storage location with a probability between 0 and 1 (rather than with a probability of either 0 or 1 as in a conventional RAM), such a RAM would have a potential for constructing neural networks which mimicked more closely than hitherto the behaviour of physiological networks. (See Gorse, D., and Taylor, J. G., 1988, Phys. Lett. A. 131, 326-332; Gorse, D., and Taylor, J. G., 1989, Physica D, 34, 90-114). The term "pRAM", an abbreviation for "probabilistic RAM", is used there and herein for a RAM in which a given output is produced with a given probability between 0 and 1 when a particular storage location in the RAM is addressed, rather than with a probability of either 0 or 1 as in a conventional RAM.
In International Patent Applications Nos. WO92/00572 and WO92/00573, and in a paper entitled "Hardware realisable models of neural processing", published in Proceedings of the first IEE International Conference on Artificial Neural Networks, 1989, pp 242-246 there is a description of how a pRAM may be constructed. There is described a device for use in a neural processing network, comprising a memory having a plurality of storage locations at each of which a number representing a probability is stored; means for selectively addressing each of the storage locations to cause the contents of the location to be read to an input of a comparator; a noise generator for inputting to the comparator a random number representing noise; and means for causing to appear at an output of the comparator an output signal having a first or second value depending on the values of the numbers received from the addressed storage location and the noise generator, the probability of the output signal having a given one of the first and second values being determined by the number at the addressed location.


OBJECT AND SUMMARY OF THE INVENTION

It is an object of the present invention to provide a novel neuron in which the effect of time on the output thereof is incorporated in a form which at least approximates what is currently understood to be the case with biological neurons, whilst also incorporating stochastic properties.
According to the present invention there is provided a neural device which comprises a plurality of neural elements each of which has a memory having a plurality of storage locations at each of which locations a number representing a probability is stored, means for addressing the storage locations, and means for causing to appear at the output of the element, when the storage locations are addressed, an element output signal, the probability of the output signal having a given one of first and second values being determined by the number at the addressed location, the neural elements having their outputs connected in common to means for accumulating the output signals thereof and for decaying the result of the accumulation; and thresholding means for receiving at its input the decayed result and generating an output signal at its output when the said decayed result exceeds a predetermined level.
The pRAMs may be 1-pRAMs, that is to say they have a single address input line and thus two addresses, corresponding respectively to a 0 and a 1 as the input address, and two storage locations, one for each address. Alternatively, however, the pRAMs may have a plurality of address lines, for example they may be 2-pRAMs, i.e. each pRAM has two address lines.
The temporal modelling of biological neurons is normally based on the Leaky Integrator model by Hodgin & Huxley, (Hodgin A. L. and Huxley A. F., J Physiol. (London) 117, 500, 1952). In the devices described herein

REFERENCES:
patent: 3250918 (1966-05-01), McGrogan, Jr.
patent: 4989256 (1991-11-01), Buckley
patent: 5063521 (1991-11-01), Peterson et al.
patent: 5091864 (1992-02-01), Baji et al.
patent: 5151971 (1992-09-01), Jousselin et al.
patent: 5165009 (1992-11-01), Watanabe et al.
patent: 5167009 (1992-11-01), Skeirik
patent: 5175798 (1992-12-01), Taylor et al.
patent: 5197114 (1993-03-01), Skeirik
patent: 5293459 (1994-03-01), Duranton et al.
Taylor et al, "Temporal Pattern and Leaky Integrator Neurons", IEEE Inter. Neural Netword Conf., Jul. 1990.
Myers et al, "Output Functions for probability Logic Nodes", IEE 1st Conf. on Artificial Neural Networks, 1989.
Clarkson et al, "Hardware Realisable Models of Neural Processing", IEE Artificial Neural Networks, 1989.
Clarkson et al, "PRAM Automata", IEEE Inter. Workshop on Cellular Neural Networks and their applications, 16`19 Dec. 1990.
Sicherheit durch Qualitat (Elektronik 25, 1990).

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Devices for use in neural processing does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Devices for use in neural processing, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Devices for use in neural processing will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-1958195

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.