Other

Maxar Mission Solutions Inc.

Lam Research Corporation

Alan H Schoen

Andrew Jenkins

Adam Estrada

Nathan Clement

Arnold Boedihardjo

Andrew D Bailey, Iii

Greg Sexton

Techniques for quantifying accuracy of a prediction model that has been trained on a data set parameterized by multiple features are provided. The model performs in accordance with a theoretical performance manifold over an intractable input space in connection with the features. A determination is made as to which of the features are strongly correlated with performance of the model. Based on the features determined to be strongly correlated with performance of the model, parameterized sub-models are created such that, in aggregate, they approximate the intractable input space. Prototype exemplars are generated for each of the created sub-models, with the prototype exemplars for each created sub-model being objects to which the model can be applied to result in a match with the respective sub-model. The accuracy of the model is quantified using the generated prototype exemplars. A recommendation engine is provided for when there are particular areas of interest.

Techniques for deriving and/or leveraging application-centric model metric

Techniques for recommending a prediction model from among a number of different prediction models are provided. Each of these prediction models has been trained based on a respective training data set, and each performs in accordance with a respective theoretical performance manifold. An indication of a region definable in relation to the theoretical performance manifolds of the different prediction models is received as input. For each of the different prediction models, the indication of the region is linked to features parameterizing the respective performance manifold; and one or more portions of the respective performance manifold is/are identified based on the features determined by the linking, the portion(s) having a volume and a shape that collectively denote an expected performance of the respective model for the input. The expected performance of the prediction models for the input is compared. Based on the comparison, one or more of the models is/are suggested.

A plasma etch processing chamber configured to clean a bevel edge of a substrate is provided. The chamber includes a bottom edge electrode and a top edge electrode defined over the bottom edge electrode. The top edge electrode and the bottom edge electrode are configured to generate a cleaning plasma to clean the bevel edge of the substrate. The chamber includes a gas feed defined through a top surface of the processing chamber. The gas feed introduces a processing gas for striking the cleaning plasma at a location in the processing chamber that is between an axis of the substrate and the top edge electrode. A pump out port is defined through the top surface of the chamber and the pump out port located along a center axis of the substrate. A method for cleaning a bevel edge of a substrate is also provided.

Method and system for distributing gas for a bevel edge etcher

A set of tiles each of which is distinct from the other tiles in the set is arranged in a particular circle tiling having various unusual properties. As a result of these properties, each one of a number of sub-sets of these tiles may be identified by a characteristic color or other characterizing mark, and these sub-sets, so identified, may be used in various ways as a recreational puzzle, as a game, as an educational tool, for aesthetic purposes, and for a variety of other uses.

Set of tiles for covering a surface

A set of tiles for covering a regular polygon having an even number of sides is composed of tiles each of which is distinct from the other tiles in the set. The tiles in the set may be combined so as to form the regular polygon in a number of ways which increases very rapidly with increasing numbers of sides. The tiles of the invention may be used as a recreational puzzle, as a game, as an educational tool, for aesthetic purposes, and for a variety of other uses.

Growing community of inventors

Carbondale, IL, United States of America

Alan H Schoen