Abstract: In an approach to unsupervised feature learning for relational data, a computer trains one or more entity aware autoencoders on one or more tables in a relational database, where each of the one or more entity aware autoencoders corresponds to one of the one or more tables in the relational database, and where each of the one or more entity aware autoencoders are comprised of an encoder and a decoder. A computer transforms each of the one or more tables in the relational database with the encoder of the corresponding trained entity aware autoencoder. A computer joins a first transformed table of the one or more tables in the relational database with each remaining one or more transformed tables in the relational database to form one or more joined tables. A computer aggregates the one or more joined tables. A computer outputs one or more feature representations.

Abstract: A method, computer system, and computer program product for enhancing feature engineering based on unsupervised learning of associated external knowledge embedding are provided. The embodiment may include receiving, by a processor, input data as a table and a name of a column. The embodiment may also include analyzing the column to identify multisets of concepts or sequences of concepts. The embodiment may further include automatically expanding the column by linking the identified multisets or the sequences of the concepts with corresponding concepts in an external knowledge graph. The embodiment may also include training a neural network to learn embedding vectors of concept multi-sets in the expanded column of the tables, wherein the training is unsupervised without provision of labels of data when the neural network learns an embedding of the multisets of concepts with an objective to minimize a reconstruction error of the identified multisets of concepts.

Abstract: Detecting an anomaly in deep learning programming can include receiving a deep learning program with neural network. A pre-trained machine learning model can be run with the deep learning program with neural network as input. The pre-trained machine learning model detects whether the neural network includes a detaching subgraph. Responsive to detecting that the neural network includes a detaching subgraph, a location of the deep learning program causing the detaching subgraph can be output. The neural network of the deep learning program can be run in training mode and weight gradients associated with training of the neural network can be monitored. Based on the monitoring, occurrence of one or more detaching subgraphs can be detected. Responsive to detecting a detaching subgraph, the detaching subgraph can be output. A suggestion to correct the deep learning program can also be output.

Abstract: Techniques facilitating automatic feature extraction from a relational database are provided. In an embodiment, a method can include generating an entity graph based on a relational database, wherein the entity graph comprises a first node associated with a first table in the relational database and a second node associated with a second table in the relational database. In another embodiment, the method can include joining the first table and the second table based on an edge between the first table and the second table defined by the entity graph, wherein a resulting joined table is connected by a column of data. In another embodiment, the method can include extracting a feature from the column of data using a data mining algorithm selected from a set of data mining algorithms based on a type of data in the column of data.

Abstract: Techniques facilitating automatic feature extraction from a relational database are provided. In an embodiment, a method can include generating an entity graph based on a relational database, wherein the entity graph comprises a first node associated with a first table in the relational database and a second node associated with a second table in the relational database. In another embodiment, the method can include joining the first table and the second table based on an edge between the first table and the second table defined by the entity graph, wherein a resulting joined table is connected by a column of data. In another embodiment, the method can include extracting a feature from the column of data using a data mining algorithm selected from a set of data mining algorithms based on a type of data in the column of data.

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 intelligent unsupervised learning of visual alphabets by one or more processors are described. A visual three-dimensional (3D) alphabet may be learned from one or more images using a machine learning operations. A set of 3D primitives representing the visual 3D alphabet may be provided.

Abstract: Embodiments for intelligent automated feature engineering for relational data in a computing environment by a processor. Indices may be automatically selected and built from one or more columns of one or more tables in a relational database using one or more automated feature engineering models that include a set of queries. One or more features may be determined using a set of queries of an automated feature engineering models to execute for a scoring operation.

Abstract: Embodiments for intelligent unsupervised learning of visual alphabets by one or more processors are described. A visual three-dimensional (3D) alphabet may be learned from one or more images using a machine learning operations. A set of 3D primitives representing the visual 3D alphabet may be provided.

Abstract: Techniques facilitating automatic feature extraction from a relational database are provided. In an embodiment, a method can include generating an entity graph based on a relational database, wherein the entity graph comprises a first node associated with a first table in the relational database and a second node associated with a second table in the relational database. In another embodiment, the method can include joining the first table and the second table based on an edge between the first table and the second table defined by the entity graph, wherein a resulting joined table is connected by a column of data. In another embodiment, the method can include extracting a feature from the column of data using a data mining algorithm selected from a set of data mining algorithms based on a type of data in the column of data.

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 automatic visualization and explanation of feature learning output for predictive modeling in a computing environment by a processor. A degree of importance score may be assigned to one or more features from a relational database according to the machine learning model. A visualization graph of one or more join paths and the one or more features with the degree of importance score to predict a target variable may be generated.

Abstract: Embodiments for automatic feature learning for predictive modeling in a computing environment by a processor. A first table and a second table are joined based on an edge between the first table and the second table defined by an entity graph thereby creating a resulting joined table that is connected by a column of data. The resulting joined table is used as an input into one or more neural network operations that transform the resulting joined table to one or more features to predict a target variable.

Abstract: Embodiments for analyzing images by one or more processors are described. An image is received. An object appearing in the image is detected. A scene graph is generated for the object. At least one transformational matrix is determined for the object. The at least one transformational matrix is associated with rendering the object as the object appears in the image based on the scene graph.

Abstract: Embodiments for analyzing images by one or more processors are described. An image is received. An object appearing in the image is detected. A scene graph is generated for the object. At least one transformational matrix is determined for the object. The at least one transformational matrix is associated with rendering the object as the object appears in the image based on the scene graph.

Abstract: Embodiments for automatic feature learning for predictive modelling in a computing environment by a processor. A first table and a second table are joined based on an edge between the first table and the second table defined by an entity graph thereby creating a resulting joined table that is connected by a column of data. The resulting joined table is used as an input into one or more neural network operations that transform the resulting joined table to one or more features to predict a target variable.

Abstract: Techniques facilitating automatic feature extraction from a relational database are provided. In an embodiment, a method can include generating an entity graph based on a relational database, wherein the entity graph comprises a first node associated with a first table in the relational database and a second node associated with a second table in the relational database. In another embodiment, the method can include joining the first table and the second table based on an edge between the first table and the second table defined by the entity graph, wherein a resulting joined table is connected by a column of data. In another embodiment, the method can include extracting a feature from the column of data using a data mining algorithm selected from a set of data mining algorithms based on a type of data in the column of data.

Abstract: Embodiments for automatic data preprocessing for a machine learning operation by a processor. For each data instance in a set of data instances, a sequence of actions may be automatically learned in a reinforcement learning environment to be applied for preprocessing each data instance separately.

Abstract: Techniques facilitating automatic feature extraction from a relational database are provided. In an embodiment, a method can include generating an entity graph based on a relational database, wherein the entity graph comprises a first node associated with a first table in the relational database and a second node associated with a second table in the relational database. In another embodiment, the method can include joining the first table and the second table based on an edge between the first table and the second table defined by the entity graph, wherein a resulting joined table is connected by a column of data. In another embodiment, the method can include extracting a feature from the column of data using a data mining algorithm selected from a set of data mining algorithms based on a type of data in the column of data.

Abstract: Techniques facilitating automatic feature extraction from a relational database are provided. In an embodiment, a method can include generating an entity graph based on a relational database, wherein the entity graph comprises a first node associated with a first table in the relational database and a second node associated with a second table in the relational database. In another embodiment, the method can include joining the first table and the second table based on an edge between the first table and the second table defined by the entity graph, wherein a resulting joined table is connected by a column of data. In another embodiment, the method can include extracting a feature from the column of data using a data mining algorithm selected from a set of data mining algorithms based on a type of data in the column of data.