High order information processing method by means of a neural ne

Image analysis – Histogram processing – For setting a threshold

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

382 15, 395101, G06K 900

Patent

active

051539233

DESCRIPTION:

BRIEF SUMMARY
TECHNICAL

The present invention relates to a method for constructing a neural network capable of solving problems such as recognition, which are difficult to solve by means of a conventional computer as well as the application thereof to pattern recognition, initial visual sensation processing, movement control, numerical analysis, etc.


BACKGROUND ART

Heretofore, learning, memorization, identification, etc. are discussed in "Parallel Distributed Processing I and II" by Mcclelland and Rumelhart (MIT Press, 1986). However neither knowledge on the cerebral physiology of living body, which is developed in the highest degree, is reflected therein nor discussion is done on the structure of the network, the speed of calculation, etc., which are problems, in the case where a practical application thereof is premised. In addition, no method for constructing the network for an object depending on the time is described therein.
On the other hand, a method for solving a neural network as an energy minimizing method is described in "Hop-field & Tank" (Science, Vol. 233 pp. 625-633 (1986)). However the neural network dealt with there is restricted to a monolayer and any solution cannot be obtained within a practical calculation time.
Hereinbelow a conventional technique by the minimum and maximum searching method for solving the neural network as an energy minimizing problem will be explained.
When the minimum (maximum) of a given cost function E was obtained, in the case where the cost function had a number of extreme values, generally it was difficult to obtain this minimum by the definite hill-climbing method as a conventional method. This is because, when a value in the neighborhood of a certain extreme value is given as an initial value, the system falls in a minimum value close thereto because of the fact that the method is definite and it is not possible to get out therefrom. Heretofore, in order to solve this problem, a definite hill-climbing method called simulated annealing has been proposed. Simply speaking, it is tried to reach the final destination by making it possible not only to climb the mountain but also to descend therefrom with a certain probability. By the method most widely utilized, taking a problem for obtaining the smallest value of E as an example, it can be solved as follows. At first, instead of considering directly the cost function E, it is considered to maximize a Bolzmann distribution P-exp (-E/T). The parameter T introduced therein is called temperature, which is introduced in order to generate random noise to make it possible to treat the problem statistically. Consequently, when the value obtained by calculation reaches a minimum value, it is necessary to set T at 0 and to make it stay at the minimum value without error. It is the greatest problem of the simulated annealing to determine the cooling schedule how to decrease T.
As discussed in IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 6, pp. 720-741, (1985), by the Geman brothers' schedule widely utilized heretofore, states are generated according to the Bolzmann distribution to fulfil T(t)=T.sub.0 /log (t+1), to being a positive constant. Here t corresponds to the number of Monte Carlo simulations and here it is defined that it represents the time. It is a matter of course that as t increases, T(t) approaches 0. Although several examples, in which this method can be successfully applied, have been already reported, there are many cases where it is not always successfully applied. Further, as discussed recently by Szu and Hartley in Physics Letters, vol. 123, pp. 157-161, (1987), in order to increase the convergence to the maximum of P, another schedule of T(t)=T.sub.0 /t+1 has been proposed, which uses Lorenz distribution having a wider spread in stead of Bolzmann distribution. However a disadvantage common to these schedules is that no function form of the cost function, which is to be minimized, is taken into account at all. It is not reflected on T(t) what kind of cost barriers (difference in the cost be

REFERENCES:
patent: 4805225 (1989-02-01), Clark
patent: 4941122 (1990-07-01), Weideman
patent: 4965725 (1990-10-01), Rutenberg
patent: 5003490 (1991-03-01), Castelaz et al.
Koplowitz et al., "Motivation System for a Robot", IEEE Trans. on Systems, Man and Cybernetics, No. 4, Jul. 1973, pp. 425-428.
Mesrobian et al., "Discrimination of Natural Textures: . . . ," IEEE 1st Int. Conf. on Neural Nets Jun. 1987, pp. IV-247-258.
Fukushima et al. "Neocognitron: . . . ," N. H. K. Laboratory Note, No. 236, Sep. 1986, pp. 1, 3-13.
Carpenter et al., "The Art of Adaptive Pattern Recognition . . . ," Computer, vol. 21, No. 3, Mar. 1988 pp. 77-88.

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

High order information processing method by means of a neural ne does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with High order information processing method by means of a neural ne, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and High order information processing method by means of a neural ne will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-1196484

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