Abstract: Broadly speaking, embodiments of the present techniques provide a method for reducing errors in the outputs of machine learning, ML, models on a potential output of the models to resolve any inconsistencies before outputting a final result from the models. The final result respects a set of rules or constraints, which may include logical constraints. Advantageously, this reduces the risk of a model outputting a result which violates some rules associated with the overall task of the model, which could be dangerous or provide a poor user experience.

Abstract: Generate, from a logical formula, a directed acyclic graph having a plurality of nodes and a plurality of edges. Assign an initial embedding to each mode and edge, to one of a plurality of layers. Compute a plurality of initial node states by using feed-forward networks, and construct cross-dependent embeddings between conjecture node embeddings and premise node embeddings. Topologically sort the DAG with the initial embeddings and node states. Beginning from a lowest rank, compute layer-by-layer embedding updates for each of the plurality of layers until a root is reached. Assign the embedding update for the root node as a final embedding for the DAG. Provide the final embedding for the DAG as input to a machine learning system, and carry out the automatic theorem proving with same.

Abstract: A method for optimal design of experiments for joint model selection and parametrization determination of a symbolic mathematical model includes: determining a prediction value for a given inquiry data point, functional form and parameterization for conducting an experiment relating to a system under investigation; assuming a set of input-output data pairs as a starting point in a model discovery process relating to the system under investigation; performing discovery of symbolic models minimizing complexity for a bounded misfit, or minimizing a misfit measure, subject to bounded complexity; determining a new data point through optimal experimental design that informs best as for the underlying symbolic models; and updating a posterior distribution, given results of the experiment relating to the system under investigation for the determined new data point to enable informed assessment among a plurality of functional forms and parameterizations. An apparatus configured to perform the method is also provided.

Abstract: A method of improving computing efficiency of a computing device for language-independent problem solving and reasoning includes receiving a query from a user, which is decomposed into one or more sub-queries arranged according to a tree structure. The one or more sub-queries are executed in a knowledge base. The results of the executed one or more sub-queries are received and composed into a query response. The query response is transmitted to the user.

Abstract: An information processing system, a computer readable storage medium, and a computer-implemented method, collect tables from a corpus of documents, convert the collected tables to flattened table format and organized to be searchable by schema-less queries. A method collects tables, extracts feature values from collected table data and collected table meta-data for each collected table. A table classifier classifies each collected table as being a type of table. Based on the classifying, the collected table is converted to a flattened table including table values that are the table data and the table meta-data of the collected table. Dependencies of the data values are mapped. The flattened table and mapped dependencies are stored in a triple store searchable by schema-less queries. The table classifier learns and improves its accuracy and reliability. Dependency information is maintained among a plurality of database tables. The dependency information can be updated at variable update frequency.

Abstract: Provide a background theory applicable to a scientific problem as input to a computerized generative reasoner, which in turn produces a plurality of provable conjectures applicable to the problem, based on the input. Provide the plurality of provable conjectures and a set of input training data to a computerized model inference engine, which fits the input training data to the plurality of provable conjectures to obtain at least one candidate symbolic model reflecting scientific laws associated with the problem. Reduce a search space of a computerized prediction module by providing to the computerized prediction module the at least one candidate symbolic model. Provide new data to the computerized prediction module, which searches in the reduced search space to make a prediction related to the problem based on the new data and the at least one candidate symbolic model.

Abstract: Aspects of the invention include obtaining a set of data that includes inputs and outputs to be modelled and performing a symbolic regression to find a symbolic model that fits the inputs and the outputs of the set of data. The symbolic model is a symbolic expression discovered by the symbolic regression in a search space. Automated reasoning is performed to affect a final symbolic model that is used to obtain new outputs from new inputs based on the final symbolic model.

Abstract: An information processing system, a computer readable storage medium, and a computer-implemented method, collect tables from a corpus of documents, convert the collected tables to flattened table format and organized to be searchable by schema-less queries. A method collects tables, extracts feature values from collected table data and collected table meta-data for each collected table. A table classifier classifies each collected table as being a type of table. Based on the classifying, the collected table is converted to a flattened table including table values that are the table data and the table meta-data of the collected table. Dependencies of the data values are mapped. The flattened table and mapped dependencies are stored in a triple store searchable by schema-less queries. The table classifier learns and improves its accuracy and reliability. Dependency information is maintained among a plurality of database tables. The dependency information can be updated at variable update frequency.

Abstract: An information processing system, a computer readable storage medium, and a computer-implemented method, collect tables from a corpus of documents, convert the collected tables to flattened table format and organized to be searchable by schema-less queries. A method collects tables, extracts feature values from collected table data and collected table meta-data for each collected table. A table classifier classifies each collected table as being a type of table. Based on the classifying, the collected table is converted to a flattened table including table values that are the table data and the table meta-data of the collected table. Dependencies of the data values are mapped. The flattened table and mapped dependencies are stored in a triple store searchable by schema-less queries. The table classifier learns and improves its accuracy and reliability. Dependency information is maintained among a plurality of database tables. The dependency information can be updated at variable update frequency.

Abstract: A method of improving computing efficiency of a computing device for language-independent problem solving and reasoning includes receiving a query from a user, which is decomposed into one or more sub-queries arranged according to a tree structure. The one or more sub-queries are executed in a knowledge base. The results of the executed one or more sub-queries are received and composed into a query response. The query response is transmitted to the user.

Abstract: A method for optimal design of experiments for joint model selection and parametrization determination of a symbolic mathematical model includes: determining a prediction value for a given inquiry data point, functional form and parameterization for conducting an experiment relating to a system under investigation; assuming a set of input-output data pairs as a starting point in a model discovery process relating to the system under investigation; performing discovery of symbolic models minimizing complexity for a bounded misfit, or minimizing a misfit measure, subject to bounded complexity; determining a new data point through optimal experimental design that informs best as for the underlying symbolic models; and updating a posterior distribution, given results of the experiment relating to the system under investigation for the determined new data point to enable informed assessment among a plurality of functional forms and parameterizations. An apparatus configured to perform the method is also provided.

Abstract: Generate, from a logical formula, a directed acyclic graph having a plurality of nodes and a plurality of edges. Assign an initial embedding to each mode and edge, to one of a plurality of layers. Compute a plurality of initial node states by using feed-forward networks, and construct cross-dependent embeddings between conjecture node embeddings and premise node embeddings. Topologically sort the DAG with the initial embeddings and node states. Beginning from a lowest rank, compute layer-by-layer embedding updates for each of the plurality of layers until a root is reached. Assign the embedding update for the root node as a final embedding for the DAG. Provide the final embedding for the DAG as input to a machine learning system, and carry out the automatic theorem proving with same.

Abstract: An information processing system, a computer readable storage medium, and a computer-implemented method, collect tables from a corpus of documents, convert the collected tables to flattened table format and organized to be searchable by schema-less queries. A method collects tables, extracts feature values from collected table data and collected table meta-data for each collected table. A table classifier classifies each collected table as being a type of table. Based on the classifying, the collected table is converted to a flattened table including table values that are the table data and the table meta-data of the collected table. Dependencies of the data values are mapped. The flattened table and mapped dependencies are stored in a triple store searchable by schema-less queries. The table classifier learns and improves its accuracy and reliability. Dependency information is maintained among a plurality of database tables. The dependency information can be updated at variable update frequency.

Abstract: An information processing system, a computer readable storage medium, and a computer-implemented method, collect tables from a corpus of documents, convert the collected tables to flattened table format and organized to be searchable by schema-less queries. A method collects tables, extracts feature values from collected table data and collected table meta-data for each collected table. A table classifier classifies each collected table as being a type of table. Based on the classifying, the collected table is converted to a flattened table including table values that are the table data and the table meta-data of the collected table. Dependencies of the data values are mapped. The flattened table and mapped dependencies are stored in a triple store searchable by schema-less queries. The table classifier learns and improves its accuracy and reliability. Dependency information is maintained among a plurality of database tables. The dependency information can be updated at variable update frequency.

Abstract: An information processing system, a computer readable storage medium, and a computer-implemented method, collect tables from a corpus of documents, convert the collected tables to flattened table format and organized to be searchable by schema-less queries. A method collects tables, extracts feature values from collected table data and collected table meta-data for each collected table. A table classifier classifies each collected table as being a type of table. Based on the classifying, the collected table is converted to a flattened table including table values that are the table data and the table meta-data of the collected table. Dependencies of the data values are mapped. The flattened table and mapped dependencies are stored in a triple store searchable by schema-less queries. The table classifier learns and improves its accuracy and reliability. Dependency information is maintained among a plurality of database tables. The dependency information can be updated at variable update frequency.