Abstract: This specification provides a meta learning method of a deep learning model and a meta learning system of a deep learning model, and relates to the field of deep learning technologies. The meta learning method of a deep learning model is applied to a cluster including N processing nodes, and the method includes: obtaining a training dataset, where the training dataset includes training samples corresponding to a plurality of tasks; and performing a plurality of times of iterative training on the deep learning model based on the training dataset in parallel by using the N processing nodes in the cluster, to obtain a meta learning parameter of the deep learning model, In each time of iterative training, each of the N processing nodes learns some parameters of the deep learning model by using some training samples in the training dataset, and the some training samples correspond to a same task.

Abstract: A computer assesses language attributes of web application display text elements. The computer receives access to a selected web application. The computer parses hypertext markup language content of the web application and generating a parse tree representing the content. The computer identifies, using the parse tree, display text elements within the content and determining associated element selector queries that identify respective display text elements within the parse tree. The computer processes a set of display text elements, using a plurality of Natural Language Processing classifier models, each of the classifier models generates a relevant language prediction for the processed display text element. The computer collects, for each text element, groups of classifiers associated with substantially-similar predictions and indexed by relevant text element selector. The computer determines a target language match condition for each group.

Abstract: In a first aspect, a single layer polymer film includes 60 to 99 wt % of a crosslinked polyimide, having a gel fraction in the range of from 20 to 100% and a refractive index of 1.74 or less, and 1 to 40 wt % of a colorant. A surface of the single layer polymer film has been textured and has a maximum roughness (Spv) of 6 ?m or more, an L* color of 30 or less and a 60° gloss of 15 or less. In a second aspect, a coverlay for a printed circuit board includes the single layer polymer film of the first aspect. In third and fourth aspects, processes are disclosed for forming a single layer polymer film including a crosslinked polyimide film including a dianhydride and a diamine.

Abstract: Embodiments for providing automated machine learning visualization. Machine learning tasks, transformers, and estimators may be received into one or more machine learning composition modules. The machine learning composition modules generate one or more machine learning models. A machine learning model pipeline is a sequence of transformers and estimators and an ensemble of machine learning pipelines are an ensemble of machine learning pipelines. A machine learning model pipeline, an ensemble of a plurality of machine learning model pipelines, or a combination thereof, along with corresponding metadata, may be generated using the machine learning composition modules. Metadata may be extracted from the machine learning model pipeline, the ensemble of a plurality of machine learning model pipelines, or combination thereof.

Abstract: In accordance with an embodiment of the invention, a method is provided for personalizing machine learning models for users of an automated machine learning system, the machine learning models being generated by an automated machine learning system. The method includes obtaining a first set of datasets for training first, second, and third neural networks, inputting the training datasets to the neural networks, tuning hyperparameters for the first, second, and third neural networks for testing and training the neural networks, inputting a second set of datasets to the trained neural networks and the third neural network generating a third output data including a relevance score for each of the users for each of the machine learning models, and displaying a list of machine learning models associated with each of the users, with each of the machine learning models showing the relevance score.

Abstract: Embodiments for managing feature engineering with relational data are provided. A graphical user interface (GUI) that provides a user with the ability to upload a plurality of tables, select joins between the plurality of tables, and select keys for the joins is provided. Responsive to receiving user input indicative of selecting joins between the plurality of tables and selecting keys for the joins utilizing the GUI, the user selections are automatically validated and actions associated with at least some of the plurality of tables are dynamically performed based on the user selections. Information associated with the user selections and the validating is provided. The information includes a recommendation to link a third key in the at least some of the plurality of tables to a fourth key in the at least some of the plurality of tables.

Abstract: In a first aspect, a single layer polymer film includes 60 to 99 wt % of a crosslinked polyimide, having a gel fraction in the range of from 20 to 100% and a refractive index of 1.74 or less, and 1 to 40 wt % of a colorant. A surface of the single layer polymer film has been textured and has a maximum roughness (Spv) of 6 ?m or more, an L* color of 30 or less and a 60° gloss of 15 or less. In a second aspect, a coverlay for a printed circuit board includes the single layer polymer film of the first aspect. In third and fourth aspects, processes are disclosed for forming a single layer polymer film including a crosslinked polyimide film including a dianhydride and a diamine.

Abstract: In accordance with an embodiment of the invention, a method is provided for personalizing machine learning models for users of an automated machine learning system, the machine learning models being generated by an automated machine learning system. The method includes obtaining a first set of datasets for training first, second, and third neural networks, inputting the training datasets to the neural networks, tuning hyperparameters for the first, second, and third neural networks for testing and training the neural networks, inputting a second set of datasets to the trained neural networks and the third neural network generating a third output data including a relevance score for each of the users for each of the machine learning models, and displaying a list of machine learning models associated with each of the users, with each of the machine learning models showing the relevance score.

Abstract: Embodiments for managing feature engineering with relational data are provided. A graphical user interface (GUI) that provides a user with the ability to upload a plurality of tables, select joins between the plurality of tables, and select keys for the joins is provided. Responsive to receiving user input indicative of selecting joins between the plurality of tables and selecting keys for the joins utilizing the GUI, the user selections are automatically validated and actions associated with at least some of the plurality of tables are dynamically performed based on the user selections. Information associated with the user selections and the validating is provided. The information includes a recommendation to link a third key in the at least some of the plurality of tables to a fourth key in the at least some of the plurality of tables.

Abstract: Embodiments for providing automated machine learning visualization. Machine learning tasks, transformers, and estimators may be received into one or more machine learning composition modules. The machine learning composition modules generate one or more machine learning models. A machine learning model pipeline is a sequence of transformers and estimators and an ensemble of machine learning pipelines are an ensemble of machine learning pipelines. A machine learning model pipeline, an ensemble of a plurality of machine learning model pipelines, or a combination thereof, along with corresponding metadata, may be generated using the machine learning composition modules. Metadata may be extracted from the machine learning model pipeline, the ensemble of a plurality of machine learning model pipelines, or combination thereof.

Abstract: Annotating a document in a data processing system, wherein the document includes a first content section and a data structure, can include receiving a request to annotate the document, wherein the request comprises an annotation, and an identification of the document to annotate, and creating a second content section comprising the annotation. The data structure can be updated with a reference to the second content section thereby making the second content section available as an annotation in association with the document.

Abstract: An event scheduling request is received, and a disruption factor is associated with each of a plurality of invitees. The disruption factor is based upon, at least in part, an event parameter and at least one invitee attribute. An event is scheduled based upon, at least in part, the disruption factors associated with each of the plurality of invitees.

Abstract: Annotating a document in a data processing system, wherein the document includes a first content section and a data structure, can include receiving a request to annotate the document, wherein the request comprises an annotation, and an identification of the document to annotate, and creating a second content section comprising the annotation. The data structure can be updated with a reference to the second content section thereby making the second content section available as an annotation in association with the document.

Abstract: A method and apparatus for determining a data mapping relationship between a source database table and a target database table are included. The method includes obtaining attribute values of an attribute other than a primary key and corresponding primary key value sets from plural rows of data in a source database table, and obtaining attribute values of a specific attribute other than a corresponding primary key and corresponding primary key value sets from plural rows of data in the target database table. A determination is made as to whether the attribute of the source database table and the specific attribute of the target database table have a potential data mapping relationship. If the determination is affirmative, a data mapping relationship is determined therebetween.

Abstract: An event scheduling request is received, and a disruption factor is associated with each of a plurality of invitees. The disruption factor is based upon, at least in part, an event parameter and at least one invitee attribute. An event is scheduled based upon, at least in part, the disruption factors associated with each of the plurality of invitees.