发明名称 |
Neural network, neuron, and method suitable for manufacturing process parameter estimation. |
摘要 |
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 (41) is non-segmented to model the entire manufacturing process (80). The first (42) and second (43) 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. <IMAGE> |
申请公布号 |
EP0653714(A3) |
申请公布日期 |
1996.05.22 |
申请号 |
EP19940117232 |
申请日期 |
1994.11.02 |
申请人 |
MOTOROLA, INC. |
发明人 |
HOLT, JAMES C. |
分类号 |
G06G7/60;G06F15/18;G06N3/04;G06N3/06 |
主分类号 |
G06G7/60 |
代理机构 |
|
代理人 |
|
主权项 |
|
地址 |
|