Abstract: Classification of spatial patterns on wafer maps is generally described. In one example, a method includes applying K-means type clustering to wafer maps comprising one or more spatial patterns to group one or more clusters comprising wafer maps having similar spatial patterns and producing a dendrogram using a clustering process to display the one or more clusters.

Abstract: Systems and methods provide for preprocessing non-metric response categories in order to efficiently cluster or partition predictors have similar responses. The non-metric response categories are transformed into distance vectors by calculating a frequency count for the response, transforming the frequency count to a proportional value, and calculating a distance vector using the vector of proportional values.

Abstract: A computer implemented method for ordering a plurality of entities by computing a dissimilarity matrix based on a plurality of probabilities. The pluralities of probabilities are determined based on a plurality of classes. A weighted distance matrix is computed based the dissimilarity matrix. A plurality of rank ordered sequence candidates based at least in part on the sum of weighted distances between neighboring entities in the rank ordered sequence is calculated. Other embodiments are described in the claims.

Abstract: Classification of spatial patterns on wafer maps is generally described. In one example, a method includes applying K-means type clustering to wafer maps comprising one or more spatial patterns to group one or more clusters comprising wafer maps having similar spatial patterns and producing a dendrogram using a clustering process to display the one or more clusters.

Abstract: A computer implemented method for ordering a plurality of entities by computing a dissimilarity matrix based on a plurality of probabilities. The pluralities of probabilities are determined based on a plurality of classes. A weighted distance matrix is computed based the dissimilarity matrix. A plurality of rank ordered sequence candidates based at least in part on the sum of weighted distances between neighboring entities in the rank ordered sequence is calculated. Other embodiments are described in the claims.

Abstract: A method and apparatus for determining the minimum zone for an array of features with a true position tolerance. In one embodiment, a target function is defined according to a deviation value of each of at least two features from an array of features having a maximum deviation between an actual position and a nominal position. Once defined, the target function is minimized to determine a rotation parameter, a horizontal translation parameter and a vertical translation parameter that provide a minimum target function value as a minimum of the maximum deviation for the array of features. In one embodiment, an inspection report may be generated for the array of features, including at least the minimum, maximum deviation value, as well as the rotation parameter, the horizontal translation parameter and the vertical translation parameter that provide the minimum target function value. Other embodiments are described and claimed.

Abstract: A method and apparatus for determining the minimum zone for an array of features with a true position tolerance. In one embodiment, a target function is defined according to a deviation value of each of at least two features from an array of features having a maximum deviation between an actual position and a nominal position. Once defined, the target function is minimized to determine a rotation parameter, a horizontal translation parameter and a vertical translation parameter that provide a minimum target function value as a minimum of the maximum deviation for the array of features. In one embodiment, an inspection report may be generated for the array of features, including at least the minimum, maximum deviation value, as well as the rotation parameter, the horizontal translation parameter and the vertical translation parameter that provide the minimum target function value. Other embodiments are described and claimed.

Abstract: Systems and methods provide for preprocessing non-metric response categories in order to efficiently cluster or partition predictors have similar responses. The non-metric response categories are transformed into distance vectors by calculating a frequency count for the response, transforming the frequency count to a proportional value, and calculating a distance vector using the vector of proportional values.