Abstract: Gas distribution apparatuses described herein include a mixing plate adjacent a back plate of a showerhead. The mixing plate has a back surface and a front surface defining a thickness of the mixing plate. The mixing plate has a mixing channel comprising a top portion and a bottom portion defining a mixing channel length and at least two gas inlets in fluid communication with the top portion of the mixing channel. The gas distribution apparatus also includes a mixer disposed within the thickness of the mixing plate in the top portion of the mixing channel. The mixer has a top plate and a mixer stem extending from the top plate and a plurality of blades positioned along the mixer stem length. Also provided are processing chambers including the gas distribution apparatuses described herein.

Abstract: A method and system for characterizing a state of health of a winding of an electric machine are provided. The winding may include one or more stator windings in an electric machine, for example, a permanent magnet synchronous machine (PMSM). The method comprises: applying a voltage pulse to the winding; measuring a phase current signal of a current supplied to the winding; determining a high-frequency transient current based on the phase current signal. The state of health of the winding may be calculated as a function of change in frequency spectrum of the high-frequency transient current. The method may include calculating a plurality of packets using a wavelet packet decomposition of the high-frequency transient current; and determining one or both of: the state of health or a classification of degradation, using an indicator based upon at least one packet of the plurality of packets.

Abstract: In an example embodiment an applications (apps) intelligence framework is utilized to quickly operationalize machine learned models (of different use cases, products, or applications) and take them to production through a set of predetermined pipelines. The app server may include a model configuration component to allow an entity to configure a model for an entity's specific use case. This configuration is then passed to a model generation component in the machine learning component, which acts to generate the specific model for the entity's use case using the configuration. An intelligent scheduling component may then be used to schedule retraining of the specific model at particular intervals. Notably, the intelligent scheduling component is itself a machine learned model (in one example embodiment a neural network) that is trained to dynamically output a training interval for a particular model based on various features.

Abstract: In an example embodiment, a model generation component may additionally assign various cloud resources to a machine learned model so that the training or retraining of the model can be performed using these resource. The containers may be weighted to handle model generation work of different weight. Having one single configuration for a container responsible for generating all models leads to overuse of hardware resources because machine learning algorithms are very resource intensive, and thus dynamically selecting the weight improves hardware utilization.

Abstract: Various examples are directed to systems and methods for identifying database records in a database table. A database management system receives a search request comprising a first set of strings associated with a first column of the database table and a second set of strings associated with a second column of the database table. The database management system selects a set of first column keywords using the first set of strings and executes a first tier query at the database table. Responsive to determining that no database record returned by the first tier query has a relevance score greater than a threshold value, the database management system executes a second tier query at the database table.

Abstract: A method of processing raw data as it is received from a data provider via an input channel is disclosed. Values are derived from the raw data as it is received from the data provider via the input channel. The derived values correspond to custom fields of a summary table. The summary table is configured to store a summary of the raw data. The custom fields correspond to data capable of improving an analysis of an entity by an analysis tool. The derived values are inserted into the custom fields of the summary table. Access to the summary table is provided as enriched data for use by the analysis tool to improve the analysis of the entity.

Abstract: A computing architecture is optimized for the reuse of machine learning model. A request is received for a machine learning model recommendation that specifies parameters associated with a desired machine learning model (e.g., schema, etc.). Thereafter, a machine learning-based discovery model, recommends at least one machine learning model (to reuse) based on the parameters specified in the request. Next, data characterizing the recommended at least one machine learning model is provided (e.g., loaded into memory, displayed in a graphical user interface, transmitted to a remote computing system, and/or stored in physical persistence, etc.). In some variations, a graphical user interface can be rendered that allows a client application to select one of the recommended machine learning models and, further optionally, to activate the selected machine learning models. Related apparatus, systems, techniques and articles are also described.

Abstract: Example embodiments for classification are described. In an example embodiment, a request including a text term to be classified is received from a source system via a communication network at a computer system. A rule associated with the text term is accessed, in which the rule indicates at least one classifier of a plurality of classifiers installed at the computer system. Classification information for the text term is generated at the computer system using the at least one classifier indicated by the rule. The generated classification information includes a classification selected from a taxonomy by the at least one classifier. The generated classification information is transmitted via the communication network to the source system.

Abstract: Various examples are directed to systems and methods for identifying database records in a database table. A database management system receives a search request comprising a first set of strings associated with a first column of the database table and a second set of strings associated with a second column of the database table. The database management system selects a set of first column keywords using the first set of strings and executes a first tier query at the database table, the first tier query comprising, a must clause based at least in part on the set of first column keywords and a should clause based at least in part on a set of second column keywords. Responsive to determining that no database record returned by the first tier query has a relevance score greater than a threshold value, the database management system executes a second tier query at the database table.

Abstract: A method of processing raw data as it is received from a data provider via an input channel is disclosed. Values are derived from the raw data as it is received from the data provider via the input channel. The derived values correspond to custom fields of a summary table. The summary table is configured to store a summary of the raw data The custom fields correspond to data capable of improving an analysis of an entity by an analysis tool. The derived values are inserted into the custom fields of the summary table. Access to the summary table is provided as enriched data for use by the analysis tool to improve the analysis of the entity.

Abstract: Example embodiments for augmenting master data schema are described. In an example embodiment, schema of master data to be employed by a plurality of applications are accessed. First additional information is added to the schema, wherein the first additional information is to be employed by each of the plurality of applications in accessing the master data. After the adding of the first additional information, second additional information is added to the schema, wherein the second additional information is to be employed by a first corresponding one of the plurality of applications in accessing the master data. In some example embodiments, third additional information is added to the schema, wherein the third additional information is to be employed by a second corresponding one of the plurality of applications in accessing the master data.

Abstract: Example embodiments for master data synchronization for multiple applications are described. In an example embodiment, master data to be employed by a plurality of applications, as well as schema for the master data, are accessed. One or more publication requests to store the master data and the schema of the master data to a master data store accessible by the plurality of applications are generated. The schema may be cached locally to one or more of the applications.

Abstract: Example embodiments for classification are described. In an example embodiment, a request including a text term to be classified is received from a source system via a communication network at a computer system. A rule associated with the text term is accessed, in which the rule indicates at least one classifier of a plurality of classifiers installed at the computer system. Classification information for the text term is generated at the computer system using the at least one classifier indicated by the rule. The generated classification information includes a classification selected from a taxonomy by the at least one classifier. The generated classification information is transmitted via the communication network to the source system.

Abstract: Example embodiments for augmenting master data schema are described. In an example embodiment, schema of master data to be employed by a plurality of applications are accessed. First additional information is added to the schema, wherein the first additional information is to be employed by each of the plurality of applications in accessing the master data. After the adding of the first additional information, second additional information is added to the schema, wherein the second additional information is to be employed by a first corresponding one of the plurality of applications in accessing the master data. In some example embodiments, third additional information is added to the schema, wherein the third additional information is to be employed by a second corresponding one of the plurality of applications in accessing the master data.

Abstract: Example embodiments for master data synchronization for multiple applications are described. In an example embodiment, master data to be employed by a plurality of applications, as well as schema for the master data, are accessed. One or more publication requests to store the master data and the schema of the master data to a master data store accessible by the plurality of applications are generated. The schema may be cached locally to one or more of the applications.