Patent
1993-08-27
1996-02-20
MacDonald, Allen R.
395 24, G06F 1518
Patent
active
054936322
ABSTRACT:
A neural network provides faster learning speed and simplified overall structure through use of the concept of indirect association and a method for operating the same. The neural network is constructed as a CLCAM comprising an input-side single layer perceptron adapted to realize direct associations (X.sub.i, Z.sub.1i) as linearly separable problems with respect to given inputs (X.sub.i) and first intermediate states (Z.sub.1i) derived by the user, an output-side single layer perceptron adapted to realize direct associations (Z.sub.2i,Y.sub.i) as linearly separable problems with respect to given outputs (Y.sub.i) and second intermediate states (Z.sub.2i) derived by the user, and a location addressable memory adapted to connect said first intermediate states (Z.sub.1i) with said second intermediate states (Z.sub.2i). The neural network is also constructed as HyLCAM comprising a single layer perceptron adapted to realize direct associations (X.sub.i,Z.sub.i) as linearly separable problems with respect to given inputs (X.sub.i) and intermediate states (Z.sub.i) manually derived by the user, and a location addressable memory adapted to receive the intermediate states (Z.sub.i) from the single layer perceptron as addresses and store given output data (Y.sub.i) as desired output values, correspondingly to the addresses.
REFERENCES:
patent: 4897811 (1990-01-01), Scofield
patent: 5107454 (1992-04-01), Niki
patent: 5222195 (1993-06-01), Alkon et al.
A High Storage Capacity Neural Net Content-Addressable Memory Hartman 1991 Dec. 31 Network 2.
Neural Net. Arch. for CAM Tarassenko et al. IEEE Feb. 1991 VLSI Implementation of a Neural Associative Memory and its Application to Vector Quantization Goodman et al. 1990 Jul. 09/Internat NN Conf. Jul. 9-13 1990.
Hybrid Location-Content Addressable Memory Wang et al. IEEE/28 Mar.-1 Apr. 1993.
Ahn Seung K.
Ko Seok B.
Lee Yoon K.
Wang Bo H.
Dorvil Richemond
Goldstar Co. Ltd.
MacDonald Allen R.
LandOfFree
Neural network employing a location addressable memory and metho 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 employing a location addressable memory and metho, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network employing a location addressable memory and metho will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1362287