Abstract: A neural-symbolic computing engine can have two or more modules that are configured to cooperate with each other in order to create one or more gradient-based machine learning models that use machine learning on i) knowledge representations and ii) reasoning to solve an issue. A model representation module in the neural-symbolic computing engine is configured to apply one or more mathematical functions, at least including a logit transform, to truth values from first order logic elements supplied from a language module of the neural-symbolic computing engine.

Abstract: A neural-symbolic computing engine can have two or more modules that are configured to cooperate with each other in order to create one or more gradient-based machine learning models that use machine learning on i) knowledge representations and ii) reasoning to solve an issue. A model representation module in the neural-symbolic computing engine is configured to apply one or more mathematical functions, at least including a log it transform, to truth values from first order logic elements supplied from a language module of the neural-symbolic computing engine.

Abstract: An artificial intelligence engine that has two or more modules cooperating with each other in order to create one or more machine learning models that use an adaptive semantic learning for knowledge representations and reasoning. The modules cause encoding the representations and reasoning from one or more sources in a particular field with terminology used by one or more human sources in that field into a set of rules that act as constraints and that are graphed into a neural network understandable by a first machine learning model, and then ii) adapting an interpretation of that set of encoded rules. The understanding of that set of encoded rules is adapted by i) allowing for semantically similar terms and ii) by conclusions derived from training data, to create an understanding of that set of encoded rules utilized by the machine learning model and the AI engine.

Abstract: An artificial intelligence engine that has two or more modules cooperating with each other in order to create one or more machine learning models that use an adaptive semantic learning for knowledge representations and reasoning. The modules cause encoding the representations and reasoning from one or more sources in a particular field with terminology used by one or more human sources in that field into a set of rules that act as constraints and that are graphed into a neural network understandable by a first machine learning model, and then ii) adapting an intrepetation of that set of encoded rules. The understanding of that set of encoded rules is adapted by i) allowing for semantically similar terms and ii) by conclusions derived from training data, to create an understanding of that set of encoded rules utilized by the machine learning model and the AI engine.

Abstract: The present invention is directed to a method and method which analyzes large amounts of information on a real-time basis with no previous static data set. Attributes of the data, which can be thought of as data concepts, that are present in the data stream are detected and isolated. These concepts are referred to as clusters and are used to ultimately determine the semantics of the data stream. The streaming clusters have no “current membership” in the existing state of the clustering and thus the cluster sets, and their relationship to each other, must be generated and updated as the data is being received.

Abstract: A method and apparatus comprising a fast and highly effective stochastic algorithm, referred to as Simmered Greedy Optimization (SG(N)), for solving combinatorial optimization problems, including the co-clustering problem comprising simultaneously clustering two finite sets by maximizing the mutual information between the clusterings and deriving maximally predictive feature sets. Co-clustering has found application in many areas, particularly statistical natural language processing and bio-informatics. Provided are results of tests on a suite of statistical natural language problems comparing SG(N) with simulated annealing and a publicly available implementation of co-clustering, wherein using SG(N) provided superior results with far less computation.

Abstract: A knowledge base is first characterized by an association-grounded semantics collapsed language. In response to the receipt of a query of the knowledge base, the collapsed language is used to determine whether there is an indication that the knowledge base contains knowledge requested in the query. Thereafter, the collapsed language can be used to carry out a full search for the knowledge much more efficiently than would otherwise be possible. Related methods, apparatus, and articles are also described.

Abstract: Entity disambiguation resolves which names, words, or phrases in text correspond to distinct persons, organizations, locations, or other entities in the context of an entire corpus. The invention is based largely on language-independent algorithms. Thus, it is applicable not only to unstructured text from arbitrary human languages, but also to semi-structured data, such as citation databases and the disambiguation of named entities mentioned in wire transfer transaction records for the purpose of detecting money-laundering activity. The system uses multiple types of context as evidence for determining whether two mentions correspond to the same entity and it automatically learns the weight of evidence of each context item via corpus statistics. The invention uses multiple search keys to efficiently find pairs of mentions that correspond to the same entity, while skipping billions of unnecessary comparisons, yielding a system with very high throughput that can be applied to truly massive data.

Abstract: The subject matter of this specification can be embodied in, among other things, a method that includes accessing a data structure that includes information about purchasers, merchants, and financial transactions between the purchasers and the merchants and generating purchaser clusters. Generating purchaser clusters includes clustering the purchasers based on which purchasers make purchases from the same or similar merchants. Each purchaser cluster adopts associations between purchasers belonging to the purchase cluster and merchants from which these purchasers have made purchases. The method also includes generating merchant clusters, where generating the merchant clusters includes clustering merchants based on which merchants are associated with the same or similar purchase clusters and outputting profile information that characterizes typical purchases associated with one or more of the merchant clusters for use in detecting fraudulent transactions.

Abstract: A knowledge base is first characterized by an association-grounded semantics collapsed language. In response to the receipt of a query of the knowledge base, the collapsed language is used to determine whether there is an indication that the knowledge base contains knowledge requested in the query. Thereafter, the collapsed language can be used to carry out a full search for the knowledge much more efficiently than would otherwise be possible. Related methods, apparatus, and articles are also described.

Abstract: Entity disambiguation resolves which names, words, or phrases in text correspond to distinct persons, organizations, locations, or other entities in the context of an entire corpus. The invention is based largely on language-independent algorithms. Thus, it is applicable not only to unstructured text from arbitrary human languages, but also to semi-structured data, such as citation databases and the disambiguation of named entities mentioned in wire transfer transaction records for the purpose of detecting money-laundering activity. The system uses multiple types of context as evidence for determining whether two mentions correspond to the same entity and it automatically learns the weight of evidence of each context item via corpus statistics. The invention uses multiple search keys to efficiently find pairs of mentions that correspond to the same entity, while skipping billions of unnecessary comparisons, yielding a system with very high throughput that can be applied to truly massive data.