摘要:
A neural network shell has a defined interface to an application program. By interfacing with the neural network shell, any application program becomes a neural network application program. The neural network shell contains a set of utility programs that transfers data into and out of a neural network data structure. This set of utility programs allows an application program to define a new neural network model, create a neural network data structure, train a neural network, and run a neural network. Once trained, the neural network data structure can be transported to other computer systems or to application programs written in different computing languages running on similar or different computer systems.
摘要:
A neural network development utility assists a developer in generating one or more filters for data to be input to or output from a neural network. A filter is a device which translates data in accordance with a data transformation definition contained in a translate template. Source data for the neural network may be expressed in any arbitrary combination of symbolic or numeric fields in a data base. The developer selects those fields to be used from an interactive menu. The utility scans the selected field entries in the source data base to identify the logical type of each field, and creates a default translate template based on this scan. Numeric data is automatically scaled. The developer may use the default template, or edit it from an interactive editor. When editing the template, the developer may select from a menu of commonly used neural network data formats, and from a menu of commonly used primitive mathematical operations. The developer may interactively define additional filters to perform data transformations in series, thus achieving more complex mathematical operations on the data. Templates may be edited at any time during the development process. If a network does not appear to be giving satisfactory results, the developer may easily alter the template to present inputs in some other format.
摘要:
A neural network shell has a defined interface to an application program. By interfacing with the neural network shell, any application program becomes a neural network application program. The neural network shell contains a set of utility programs that transfers data into and out of a neural network data structure. This set of utility programs allows an application program to define a new neural network model, create a neural network data structure, train a neural network, and run a neural network. Once trained, the neural network data structure can be transported to other computer systems or to application programs written in different computing languages running on similar or different computer systems.
摘要:
A neural network development utility assists a developer in generating one or more filters for data to be input to or output from a neural network. A filter is a device which translates data in accordance with a data transformation definition contained in a translate template. Source data for the neural network may be expressed in any arbitrary combination of symbolic or numeric fields in a data base. The developer selects those fields to be used from an interactive menu. The utility scans the selected field entries in the source data base to identify the logical type of each field, and creates a default translate template based on this scan. Numeric data is automatically scaled. The developer may use the default template, or edit it from an interactive editor. When editing the template, the developer may select from a menu of commonly used neural network data formats, and from a menu of commonly used primitive mathematical operations. The developer may interactively define additional filters to perform data transformations in series, thus achieving more complex mathematical operations on the data. Templates may be edited at any time during the development process. If a network does not appear to be giving satisfactory results, the developer may easily alter the template to present inputs in some other format.
摘要:
An enhanced neural network shell for application programs is disclosed. The user is prompted to enter in non-technical information about the specific problem type that the user wants solved by a neural network. The user also is prompted to indicate the input data usage information to the neural network. Based on this information, the neural network shell creates a neural network data structure by automatically selecting an appropriate neural network model and automatically generating an appropriate number of inputs, outputs, and/or other model-specific parameters for the selected neural network model. The user is no longer required to have expertise in neural network technology to create a neural network data structure.
摘要:
A neural network shell has a defined interface to an application program. By interfacing with the neural network shell, any application program becomes a neural network application program. The neural network shell contains a set of utility programs that transfers data into and out of a neural network data structure. This set of utility programs allows an application program to define a new neural network model, create a neural network data structure, train a neural network, and run a neural network. Once trained, the neural network data structure can be transported to other computer systems or to application programs written in different computing languages running on similar or different computer systems.
摘要:
Embodiments of the invention provide a method for detecting changes in behavior of authorized users of computer resources and reporting the detected changes to the relevant individuals. The method includes evaluating actions performed by each user against user behavioral models and business rules. As a result of the analysis, a subset of users may be identified and reported as having unusual or suspicious behavior. In response, the management may provide feedback indicating that the user behavior is due to the normal expected business needs or that the behavior warrants further review. The management feedback is available for use by machine learning algorithms to improve the analysis of user actions over time. Consequently, investigation of user actions regarding computer resources is facilitated and data loss is prevented more efficiently relative to the prior art approaches with only minimal disruption to the ongoing business processes.
摘要:
A method and structure for a set of rules processed by combining a procedural rule engine and a pattern matching inference engine to compute and apply discounts to customer orders in an electronic commerce system. The rule processing occurs in multiple phases. First all applicable discounts are computed. Then all allowable subsets of discounts are computed. Finally, a set of discounts is selected, based on business policies, and the discounts are applied to the order line items.
摘要:
A method, apparatus and article of manufacture for problem identification and resolution using intelligent agents. In at least one embodiment, an agent is a software element configured to detect a situation (e.g., problem or problems) and take steps to preserve a context in which the situation occurs. The agent may also be configured to identify one or more courses of action (e.g., solutions) to be taken in response to the situation. In one embodiment, a user trains an agent to take a particular action upon detecting a particular problem. The training may be initiated after accessing a log containing details about the problem context and recommended courses of action.
摘要:
A system, method, and computer program product for benchmarking a stream processing system are disclosed. The method comprises generating a plurality of correlated test streams. A semantically related data set is embedded within each of the test streams in the plurality of correlated test streams. The plurality of correlated test streams is provided to at least one stream processing system. A summary is generated for each of the semantically related embedded data sets. A common identifier, which is transparent to the system being tested, is embedded within each stream in the plurality of correlated test streams. The common identifier is extracted from the output data set generated by the stream processing system. At least one of the stored copies of the summaries and the common identifier are compared to an output data set including a set of zero or more correlation results generated by the stream processing system.