Image analysis – Histogram processing – For setting a threshold
Patent
1993-11-12
1995-09-05
MacDonald, Allen R.
Image analysis
Histogram processing
For setting a threshold
395 21, 395 27, 382156, G06F 1500
Patent
active
054486840
ABSTRACT:
A neuron (100) has a null-inhibiting function so that null inputs do not affect the output of the neuron (100) or updating of its weights. The neuron (100) provides a net value based on a sum of products of each of several inputs, and corresponding weight and null values, and provides an output in response to the net value. A neural network (40) which uses such a neuron (100) has a first segmented layer (41) in which each segment (50-52) corresponds to a manufacturing process step (60-62). Each segment of the first layer (41) receives as inputs measured values associated with the process step (60-62). A second layer (42) connected to the first layer (4l), is non-segmented to model the entire manufacturing process (80). The first (41) and second (42) layers are both unsupervised and competitive. A third layer (43) connected to the second layer (42) then estimates parameters of the manufacturing process (80) and is unsupervised and noncompetitive.
REFERENCES:
patent: 4874963 (1989-10-01), Alspector
patent: 5073867 (1991-12-01), Murphy et al.
patent: 5093899 (1992-03-01), Hiraiwa
patent: 5109351 (1992-04-01), Simar, Jr.
patent: 5136687 (1992-08-01), Edelman et al.
patent: 5214745 (1993-05-01), Sutherland
patent: 5253329 (1993-10-01), Villarreal et al.
Steck, "Convergence of recurrent networks as contraction mappings", IJCNN International Joint Conference on Neural Networks, pp. 462-467 vol. 3, 7-11 Jun. 1992.
Chen et al, "ANN with two-dendrite neurons as its weight initialization"; IJCNN International Joint Conference on Neural Networks, pp. 139-146 vol. 3, 7-11 Jun. 1992.
Kim et al, "A study of dynamic behavior of a recurrent neural network for control", Proceedings of the 30th IEEE Conference on Decision and Control, pp. 150-155 vol. 1, 11-13 Dec. 1991.
Hafiz Tariq
MacDonald Allen R.
Motorola Inc.
Polansky Paul J.
LandOfFree
Neural network, neuron, and method for recognizing a missing inp 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, neuron, and method for recognizing a missing inp, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network, neuron, and method for recognizing a missing inp will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-479894