Neural network

Details Neural network Neural network

1996-11-05

1999-01-05

Downs, Robert W.

Data processing: artificial intelligence

Neural network

706 43, G06F 1518

Patent

active

058571779

DESCRIPTION:

BRIEF SUMMARY
The invention concerns a neural network of the type stated in the introductory portion of claim 1.
Neural networks are used for data processing purposes on the basis of a plurality of complexely related input parameters to give the best possible response thereto without necessarily knowing the relation between the individual input parameters. This is extremely advantageous when no such linear relation exists.
The starting point of neural networks is the ability of the human brain to identify the most important parameters in a decision-making process and to draw correct conclusions by experience. Neural networks are therefore constructed according to the same basic principles as the human brain, comprising a multitude of decision-making cells or neurons as well as connections or synapses between these.
In order to make the best possible decisions artificial neural networks therefore go through a comprehensive learning procedure before they are used in practice, and the experience thus acquired is utilized for adjusting the control parameters for the neurons and the synapses.
As far as the neurons are concerned, these control parameters comprise a threshold value which determines whether the neuron concerned fires or applies an electric pulse after having received corresponding pulses from other neurons. The fired pulses are transferred via one or more synapses to other neurons, and the strength or the amplitude of the individual pulses transferred is one of the adjustable control parameters in the network.
A plurality of learning approaches is known, by means of which the parameters can be established according to given applications, which takes place prior to putting the network into service.
These include e.g. EP-A-492 641, which discloses a neural network and a learning procedure for it. The learning procedure comprises submitting to the network an input data signal and a learning signal containing both desired and undesired data. Hereby the network will subsequently respond more expediently. If, e.g., the network controls a process system, it would be fatal if the network would e.g. cause an increase in temperature owing to specific input data which would in turn result in an increase in pressure, if the pressure was then above the value which the system could stand.
U.S. Pat. No. 5,107,454 discloses a neural network for use in pattern recognition, and this network is based on feedback, since the learning procedure is iterative, which means that the pattern concerned and the subsequent intermediate result patterns are run through the network.
EP-A-405 174 discloses a learning method which ensures that the network does not "drop" in a local maximum, which might happen if the correlation between input and output data in a region was of a certain size. The data processing system could thus not get out of these conditions, and further adaptation would not be possible.
U.S. Pat. No. 5,010,512 discloses implementation of a neural network as MOSFET transistor elements. The neurons may here be regarded as being threshold switches having several inputs. The network can be operated in two modes, a learning mode in which the control parameters of the neurons are adjusted, and an associative mode in which the control parameters are constant.
U.S. Pat. No. 4,933,871 discloses an adaptive neural network which is adapted to receive input signals from an external system. The network may be adjusted on the basis of an external signal generated by the external system in that some weight factors and thus the transfer function of the network are changed.
It may be said about prior art neural networks that following completed learning procedure they respond in the same manner to the same data sets, notwithstanding the surrounding in which the network controls a process, traffic or the like, change.
Accordingly, the object of the invention is to provide a new generation of neural networks which possess greater adaptability, and where the network is currently capable of adapting to new conditions as well as new or changed sur

REFERENCES:
patent: 4774677 (1988-09-01), Buckley
patent: 4926064 (1990-05-01), Tapang
patent: 4933871 (1990-06-01), DeSieno
patent: 5274745 (1993-12-01), Takashi
patent: 5283855 (1994-02-01), Motomura et al.
Melso et al, "A neural network solution for call routing with preferential call placement," Globecom '90, pp. 1377-1381 vol. 2, Dec. 1990.
Matsumoto et al., "A high-speed learning method for analog neural networks," IJCNN, pp. 71-76 vol. 2, Jun. 1990.
Moon et al, "An improved neural processing element using pulse coded weights," 1993 IEEE International Symposium on Circuits and Systems, pp. 2760-2763 vol. 3, May 1993.
Miyajima et al, "performances of decision feedback equalizers using neural networks under frequency selective fading channels," Communications on the move, ICCS/ISITA '92, pp. 374-378 vol. 1, Nov. 1992.

Affiliated with

Also associated with

Rating

Neural network does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Neural network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-869567