Abstract: A computer-readable recording medium has stored therein a machine learning program executable by one or more computers, the machine learning program including: an instruction for comparing a first plurality of relationship information pieces with a second plurality of relationship information pieces, the first plurality of relationship information pieces being determined in terms of an inputted configuration of a first Artificial Intelligence (AI) system and each including a plurality of attributes, the second plurality of relationship information pieces being determined in terms of a second AI system; an instruction for determining priorities of the first plurality of relationship information pieces, the priorities being based on a result of the comparing; and an instruction for outputting, as a checklist of the first AI system, one or more check items selected in accordance with the determined priorities from among a plurality of check items associated with the plurality of attributes.

Abstract: A machine learning method includes acquiring data including attendance records of employees and information indicating which employee has taken a leave of absence from work, in response to determining that a first employee of the employees has not taken a leave of absence in accordance with the data, generating a first tensor on a basis of an attendance record of the first employee and parameters associated with elements included in the attendance record, in response to determining that a second employee of the employees has taken a leave of absence in accordance with the data, modifying the parameters, and generating a second tensor on a basis of an attendance record of the second employee and the modified parameters, and generating a model by machine learning based on the first tensor and the second tensor.

Abstract: A learning device receives, for each target, learning data that represents the source of generation of a tensor including a plurality of elements which multi-dimensionally represent the features of the target over a period of time set in advance. When the target satisfies a condition set in advance, the learning device identifies the period of time corresponding to the condition in the learning data. Subsequently, the learning device generates a weighted tensor corresponding to the learning data that is at least either before or after the concerned period of time.

Abstract: A non-transitory computer-readable recording medium storing a risk analysis program for an artificial intelligence (AI) system, the analysis program being a program for causing a computer to execute processing, the processing including: acquiring a plurality of pieces of relational information that include at least two attributes among an attribute of a type of an object person, an attribute of a type of processing, and an attribute of a type of data, wherein the relational information is determined on a basis of a configuration of the AI system; determining a priority of the plurality of pieces of relational information on a basis of the attribute of the type of the object person; and outputting one or a plurality of check items selected on a basis of the determined priority from among a plurality of check items associated with each attribute as a checklist for the AI system.

Abstract: A computer-readable recording medium having stored therein a determination result presenting program executable by one or more computers, the program including instructions for calculating a first contribution of first data including multiple factors with respect to a first prediction result obtained by inputting the first data into a machine learning model; calculating, by referring to information associating a second contribution of second data including multiple factors with respect to a second prediction result obtained by inputting the second data into the machine learning model with a determination result by a user on the second prediction result, a similarity between a third contribution and a fourth contribution obtained by adjusting the first contribution and the second contribution in accordance with a first factor identified by the determination result, respectively; and controlling, based on the similarity, a priory of a determination result to be presented among determination results in the infor

Abstract: A machine learning method includes acquiring data including attendance records of employees and information indicating which employee has taken a leave of absence from work, in response to determining that a first employee of the employees has not taken a leave of absence in accordance with the data, generating a first tensor on a basis of an attendance record of the first employee and parameters associated with elements included in the attendance record, in response to determining that a second employee of the employees has taken a leave of absence in accordance with the data, modifying the parameters, and generating a second tensor on a basis of an attendance record of the second employee and the modified parameters, and generating a model by machine learning based on the first tensor and the second tensor.

Abstract: A learning device receives, for each target, learning data that represents the source of generation of a tensor including a plurality of elements which multi-dimensionally represent the features of the target over a period of time set in advance. When the target satisfies a condition set in advance, the learning device identifies the period of time corresponding to the condition in the learning data. Subsequently, the learning device generates a weighted tensor corresponding to the learning data that is at least either before or after the concerned period of time.

Abstract: A learning apparatus receives time-series data including a plurality of items and including a plurality of records corresponding to a calendar. The learning apparatus generates tensor data, based on the time-series data, including a tensor which is set calendar information and each of the plurality of items as mutually-different dimensions. With respect to a learning model that performs a tensor decomposition on input tensor data and that inputs a result of the tensor decomposition to a neural network, the learning apparatus performs a deep learning process on the neural network and learning a method of the tensor decomposition by using the tensor data as the input tensor data.

Abstract: A non-transitory computer-readable recording medium stores therein a machine learning program that causes a computer to execute a process including: generating pieces of learning data based on time series data including a plurality of items and including a plurality of records corresponding to a calendar, each of the pieces of learning data being learning data of a certain period, the certain period being composed of a plurality of unit periods, start times of the certain period of each of the pieces of learning data being different from each other for the unit period, in which each of the pieces of the learning data and a label corresponding to the start time are paired; generating, based on the generated learning data, tensor data in which a tensor is created with calendar information and the plurality of items having different dimensions; and performing deep learning of a neural network and learning of a method of tensor decomposition with respect to a learning model in which the tensor data is subjected t

Abstract: The learning device receives attendance record data constituted of a plurality of records for a plurality of employees, the attendance record data corresponding to a period of a calendar and including a plurality of records including a plurality of items. The learning devices generates exclusion data by excluding a record corresponding to an individual holiday that is differently set by the employees, and a record corresponding to a common holiday set commonly to the employees. The learning device generates, based on the generated exclusion data, tensor data in which a tensor is created with calendar information and the items including different dimensions. The learning device performs deep learning of a neural network and learning of a method of tensor decomposition with respect to a learning model in which the tensor data is subjected to the tensor decomposition as input tensor data to be inputted to the neural network.

Abstract: A method for calculating an indicator value includes: extracting features, which are mutually independent, by using data stored in a data storage unit storing, for each group of circuits implemented on a semiconductor device, the number of actual failures occurred in the group and a feature value of each feature that is a failure factor; generating an expression of a failure occurrence probability model, which represents a failure occurrence probability, which is obtained by dividing a total sum of the numbers of actual failures by the number of semiconductor devices, as a relation including a sum of products of the feature value of each of the extracted features and a corresponding coefficient, by carrying out a regression calculation using data stored in the data storage unit; and calculating an indicator value for design change of the semiconductor device from the generated expression of the failure occurrence probability model.

Abstract: The disclosed method includes: calculating a first expected value of the number of failures for each combination of a feature that is a failure factor and a first group regarding classification elements of first semiconductor devices for which a failure is analyzed and second semiconductors on which a same circuit as the first semiconductors is implemented, from first data for each first group and a predetermined expression, wherein the first data includes the number of actual failures occurred in the first group and first feature values of features; and calculating, for each feature, a first indicator value representing similarity between a distribution of the first expected values over the first groups and a distribution of the numbers of actual failures over the first groups, from the first expected value for each combination of the feature and the first group and the number of actual failures for each first group.

Abstract: A set of pareto optimal solutions that are non-dominated solutions in a solution specification space for respective items in requirement specification is extracted with a combination of a circuit configuration including a specific function and a process constraint condition. Furthermore, pareto optimal solutions are extracted for all combinations of the circuit configuration and the process constraint condition, and pareto optimal solutions are extracted for the respective process constraint conditions. When such extracted data is distributed to designers, it is possible to reduce time to generate the pareto optimal solutions, and the designers can design the optimum circuit having a desired function by using such extracted data.

Abstract: A method for calculating an indicator value includes: extracting features, which are mutually independent, by using data stored in a data storage unit storing, for each group of circuits implemented on a semiconductor device, the number of actual failures occurred in the group and a feature value of each feature that is a failure factor; generating an expression of a failure occurrence probability model, which represents a failure occurrence probability, which is obtained by dividing a total sum of the numbers of actual failures by the number of semiconductor devices, as a relation including a sum of products of the feature value of each of the extracted features and a corresponding coefficient, by carrying out a regression calculation using data stored in the data storage unit; and calculating an indicator value for design change of the semiconductor device from the generated expression of the failure occurrence probability model.

Abstract: A dummy rule generating apparatus includes a critical pattern estimating unit that determines a wiring pattern whose total perimeter length of wirings is smaller than an appropriate range based on constraints on the wirings for a circuit layout as a critical pattern. The dummy rule generating apparatus also includes a rule generating unit that generates dummy fill rules of a shape and a layout of dummy metals that increase number of dummy metals inserted in the critical pattern and decrease the number of dummy metals inserted in a wiring pattern whose total perimeter length of wirings is within an appropriate range.

Abstract: A method includes: before carrying out a timing verification processing of a semiconductor circuit, preliminarily superposing and arranging a dummy pattern template representing an arrangement pattern of dummy metal, onto a layout area defined by layout data while changing an origin position of the dummy pattern template to optimize the origin position of the dummy pattern template; and upon detecting that the result of the timing verification processing has no problem, superposing and arranging the dummy pattern template onto the layout area at the origin position of the dummy pattern template, to generate the layout data after inserting the dummy metal.

Abstract: A fault diagnosis may perform a statistical analysis based on a fault report of a semiconductor device, in order to output a feature that becomes the cause of the fault depending on a contribution of the feature to the fault. A process of grouping circuit information of the semiconductor device into N groups using one kind of feature as an index may be performed for K kinds of features, in order to group the circuit information into K×N groups. A sum total of feature quantities of partial circuits belonging to each of the groups may be output in a form of a list of learning samples.

Abstract: A set of pareto optimal solutions that are non-dominated solutions in a solution specification space for respective items in requirement specification is extracted with a combination of a circuit configuration including a specific function and a process constraint condition. Furthermore, pareto optimal solutions are extracted for all combinations of the circuit configuration and the process constraint condition, and pareto optimal solutions are extracted for the respective process constraint conditions. When such extracted data is distributed to designers, it is possible to reduce time to generate the pareto optimal solutions, and the designers can design the optimum circuit having a desired function by using such extracted data.

Abstract: A delay analysis support apparatus that supports analysis of delay in a target circuit includes an acquiring unit that acquires error information concerning a cell-delay estimation error that is dependent on a characterizing tool; an error calculating unit that calculates, based on the error information and a first probability density distribution concerning the cell delay of each cell and obtained from the cell delay estimated by the characterizing tool, a second probability density distribution that concerns the cell-delay estimation error of each cell; and an linking unit that links the second probability density distribution and a cell library storing therein the first probability density distribution.

Abstract: An apparatus that evaluates a layout of a semiconductor integrated circuit by estimating a result of planarization in manufacturing the circuit includes a unit that divides the layout into partial areas, a unit that calculates, for each partial area, at least one of a wiring density in the partial area, a total perimeter length of wirings in the partial area, and a maximum value of differences of wiring densities in adjacent partial areas adjacent to the partial area from the wiring density in the partial area as partial area data, a unit that sets ranges of the wiring density, the total perimeter length, and the maximum value from which a height variation larger than an upper limit value is expected as critical regions based on an equation corresponding to a type of the layout, and a unit that plots the critical regions and the partial area data on a same map.