A non-transitory computer-readable recording medium stores therein a learning program for causing a computer to execute a process comprising: referring to, at time of learning a computation model that is a target of deep learning and has a plurality of nodes, a storage unit in which route information that indicates a calculation route followed by a tensor in each stage of learning prior to the time of learning, and statistical information regarding a position of a decimal point used in the calculation route are associated with each other; acquiring, when executing each piece of calculation processing set in each of the plurality of nodes at the time of learning, the statistical information corresponding to the route information that reaches each of the plurality of nodes; and executing the each piece of calculation processing using the position of the decimal point specified by the acquired statistical information.

Techniques disclosed herein describe inferring user interests based on metadata of a plurality of multimedia objects captured by a plurality of users. An analysis tool receives, for each of the users, metadata describing each multimedia object in the plurality of objects associated with that user. Each multimedia object includes one or more attributes imputed to that object based on the metadata. The analysis tool identifies one or more concepts from the one or more attributes. Each concept includes at least a first attribute that co-occurs with a second attribute imputed to a first multimedia object. The analysis tool associates a first one of the plurality of users with at least one of the concepts based on the attributes imputed to multimedia objects associated with the first one of the plurality of users.

A learning method includes: counting any one of or some of the number of labels added to each of feature amount vectors included in a learning data set, the number of types of the label, the number of feature amount vectors added with the same label, and the number of data pairs used for learning of a hyperplane, by a processor; first selecting, according to a result of the counting, one or more generation methods from a plurality of previously stored generation methods that generate the data pairs from the learning data set, by the processor; generating, using the selected generation methods, the data pairs from the feature amount vectors included in the learning data set, by the processor; and first learning, using the generated data pairs, the hyperplane that divides a feature amount vector space, by the processor.

Methods for predicting network access probability of data files accessible over a computer network are provided. In one aspect, a method includes generating a primary data vector for a media file based on a stored data representation of the file, and providing the data vector for the file to an algorithm that uses past interaction information for at least one other media file from a collection of media files having a degree of similarity with the media file above a threshold similarity value. The method also includes receiving, as an output of the algorithm, a marketability score for the media file, the score indicative of a likelihood that a user will download the media file. Systems and machine-readable media are also provided.

A data processor system for monitoring a complex system, the processor system configured to receive a plurality of pieces of state information and to merge at least the pieces of state information into a piece of failure information, at least one of the pieces of state information being associated with a confidence flag, and the piece of failure information also being associated with a confidence flag. The system performs the merging by implementing a fuzzy logic technique to produce the piece of failure information while taking account of the respective confidence flag of the pieces of state information and to produce the confidence flag associated with the failure information.

Systems and methods for recognizing and/or predicting activities of a user of a mobile device are disclosed. In certain embodiments, the systems and methods may predict a future activity and/or location of a mobile device user based on current and/or historical device data and/or other personal information relating to the user. In some embodiments, probabilistic determinations and/or other statistical models may be used to predict future activities and locations of a mobile device user. The disclosed systems and methods may further utilize location and/or activity recognition and/or prediction methods to deliver personalized services to a user of a mobile device at a particular time and/or location.

A diagnosis support system obtains input information corresponding to a case, identifies a diagnosis corresponding to the case based on the input information, obtains the inference probability of the diagnosis, and displays supporting information corresponding to the inference probability of the identified diagnosis on a display unit.

The living activity inference device according to the present invention includes: an obtainer configured to obtain an energy consumption of an electric appliance; an appliance operation detector configured to identify an operational state of the electric appliance based on the energy consumption obtained by the obtainer; and an activity inferrer configured to perform an inference process of determining which one of a plurality of living activities predetermined a current living activity corresponds to, based on existing information including the operational state of the electric appliance identified by the appliance operation detector and a past living activity.

Disclosed is a method and Geographic Information System (GIS) for creating a user's proximity model in accordance with a user's feedback. The GIS creates the user's proximity model using a Dempster-Shafer technique. The GIS initializes the user's proximity model upon initializing a fuzzy set with a fuzzy membership function. The fuzzy set includes a plurality of points scattered around a reference point. The GIS creates an intermediate model using the user's proximity model by selecting a group of points from the plurality of points. The GIS receives a user feedback on the intermediate model. The GIS adapts the fuzzy membership function based on the user feedback. The GIS then updates the user's proximity model based on the fuzzy membership function which is adapted on basis of the user feedback.

A method of predicting food items consumed by a user of a food-logging application is disclosed. Loggings of consumptions of food items are received. A predictive model is generated based on the received loggings. The predictive model generates a prediction of one or more additional food items that a target user will consume or is likely to have consumed (e.g., at a particular time). The prediction is generated based on an application of the predictive model to one or more data items (e.g., data items streaming into the system in real time from the target user or other users that are relevant to food consumptions by the target user). The prediction of the consumption of the one or more additional food items by the user may then be communicated for presentation to the target user in a user interface.