Abstract: The current subject matter describes a method and system of detecting frauds or anomalous behavior. The procedures include extracting characteristics from a dataset to generate words and documents, executing a topic model to obtain the respective probabilities of appearance of a document in each latent archetype, dividing the dataset into a plurality of subsets based upon the archetypes. The formed subsets are further utilized to estimate the quantiles and calculate scores using a self-calibrating outlier model. The score of each new transaction is determined based on a single archetype or based on the sum of weighted scores determined from all the archetypes and associated statistics. Such methods are superior to a simple self-calibration outlier model without an LDA archetype.

Abstract: The present invention relates in general to the field of parallel data processing, and more particularly to machine learning and classification of extremely large volumes of unstructured gene sequence data using Collaborative Analytics Gene Sequence Classification Learning Systems and Methods.

Abstract: Methods and systems enable an omniphysical mind or descriptive self supportable by a computing device, to evaluate its current platform and seek a new or replacement platform. The descriptive system includes infrastructure for translating sensor readings into descriptive terms, comparing the descriptive terms with template requirements, and initiating an action as the result of the comparison. The descriptive system also includes infrastructure for communicating with other platforms to receive information representing functionality and/or sensor readings, to translate the information into descriptive terms, and compare the descriptive terms with template requirements. In evaluating a new or replacement platform, if template requirements are met the descriptive system reports a database that includes symbols, definitions of symbols, and processing rules, which are provided to the new/replacement system, the database comprising an infrastructure of an omniphysical mind.

Abstract: There is provided an information processing apparatus including: a sensor data generator sensing a user behavior and generating sensor data corresponding to the user behavior; a behavior recognizing unit performing a predetermined threshold value process on the sensor data to recognize the behavior exhibited by the user and generating behavior information that is information indicating the behavior exhibited by the user; a behavior manager managing the behavior information generated by the behavior recognizing unit in correspondence with the time point at which the behavior corresponding to the behavior information is exhibited; and a behavior information post-processing unit performing a predetermined post-process on the behavior information managed by the behavior manager, wherein the behavior recognizing unit further includes a plurality of behavior determination units specified to specific behaviors exhibited by the user and generates the behavior information based on the determination results of the plur

Abstract: A technique for training a neural network including an input layer, one or more hidden layers and an output layer, in which the trained neural network can be used to perform a task such as speech recognition. In the technique, a base of the neural network having at least a pre-trained hidden layer is prepared. A parameter set associated with one pre-trained hidden layer in the neural network is decomposed into a plurality of new parameter sets. The number of hidden layers in the neural network is increased by using the plurality of the new parameter sets. Pre-training for the neural network is performed.

Abstract: Methods and a system are provided for generating labeled data. A method includes encoding, by a processor-based encoder, a first labeled data into an encoded representation of the first labeled data. The method further includes modifying the encoded representation into a modified representation by adding a perturbation to the encoded representation. The method additionally includes decoding, by a processor-based decoder, the modified representation into a second labeled data.

Abstract: Methods, apparatus, and computer-readable media are provided for analyzing a cluster of communications, such as B2C emails, to generate a template for the cluster that defines transient segments and fixed segments of the cluster of communications. More particularly, methods, apparatus, and computer-readable media are provided for generating and/or applying a trained structured machine learning model for a generated template that can be used to determine, for one or more transient segments of subsequent communications, a corresponding probability that a given semantic label is the correct semantic label for extracted content of the transient segment(s).

Abstract: The current disclosure generally relates to database management systems (DBMSs) and may be generally directed to methods and systems of using artificial intelligence (i.e. machine learning and/or anticipation functionalities, etc.) to learn a user's use of a DBMS, store this “knowledge” in a knowledgebase, and anticipate the user's future operating intentions. The current disclosure may also be generally directed to associative methods and systems of constructing DBMS commands. The current disclosure may also be generally directed to methods and systems of using a simplified DBMS command language (SDCL) for associative DBMS command construction. The current disclosure may also be generally directed to artificially intelligent methods and systems for associative DBMS command construction. The current disclosure may also be generally directed to methods and systems for associative DBMS command construction through voice input.

Abstract: The current disclosure generally relates to database management systems (DBMSs) and may be generally directed to methods and systems of using artificial intelligence (i.e. machine learning and/or anticipation functionalities, etc.) to learn a user's use of a DBMS, store this “knowledge” in a knowledgebase, and anticipate the user's future operating intentions. The current disclosure may also be generally directed to associative methods and systems of constructing DBMS commands. The current disclosure may also be generally directed to methods and systems of using a simplified DBMS command language (SDCL) for associative DBMS command construction. The current disclosure may also be generally directed to artificially intelligent methods and systems for associative DBMS command construction. The current disclosure may also be generally directed to methods and systems for associative DBMS command construction through voice input.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for score normalization. One of the methods includes receiving initial training data, the initial training data comprising initial training records, each initial training record identifying input data as input and a category as output. The method includes generating a first trained predictive model using the initial training data and a training function. The method includes generating intermediate training records by inputting input data of the initial training records to a second trained predictive model, the second trained predictive model generated using the training function, each intermediate training record having a score. The method also includes generating a score normalization model using a score normalization training function and the intermediate training records.

Abstract: A computing device predicts an event or classifies an observation. A trained labeling model is executed with unlabeled observations to define a label distribution probability matrix. A label is selected for each observation. A mean observation vector and a covariance matrix are computed from the unlabeled observations selected to have each respective label. A number of eigenvalues that have a smallest value is selected from each covariance matrix and used to define a null space for each respective label. A distance value is computed for a distance vector computed to the mean observation vector and projected into the null space associated with the label selected for each respective observation. A diversity rank is determined for each respective observation based on minimum computed distance values. A predefined number of observations having highest values for the diversity rank are included in labeled observations and removed from the unlabeled observations.

Abstract: A method for electronic logging of carrier data is described. The method includes monitoring a vehicle motion status for a predetermined period and assigning a logical state to at least one duty status variable. A plurality of travel conditions capable of changing a transit period, such as weather, traffic, and construction are monitored, aggregated, and used to determine a predicted likelihood of changing the transit period. The likelihood of occurrence of a compliance rule violation is determined, based on the aggregated values, the predicted likelihood of changing the transit period, and a group of compliance rules. An indicator of the likelihood of occurrence of a compliance rule violation may be generated, and presented to any number of electronic devices. Remedial actions to avoid or mitigate the compliance rule violation may be suggested.

Abstract: A cloud learning system for smart windows is provided. The system includes at least one server configured to couple via a network to a plurality of window systems, each of the plurality of window systems having at least one control system and a plurality of windows with electrochromic windows and sensors, wherein the at least one server includes at least one physical server or at least one virtual server implemented using physical computing resources. The at least one server is configured to gather first information from the plurality of window systems, and configured to gather second information from sources on the network and external to the plurality of window systems. The at least one server is configured to form at least one rule or control algorithm usable by a window system, based on the first information and the second information, and configured to download the at least one rule or control algorithm to at least one of the plurality of window systems.

Abstract: Methods, devices, and servers for friend recommendation are provided. A user association set of a target user is obtained. Original data of each associated user in the user association set is obtained. The original data include location relationship data, associated friend data, time relationship data, or combinations thereof, between each associated user and the target user. The original data of each associated user is screened to obtain feature data to form a feature collection for each associated user. A pre-configured N-Tree prediction model is used to process the feature collection for a prediction calculation to obtain an association-predicting value for each associated user. According to the association-predicting value of each associated user, a friend user for the target user from the user association set is determined and recommended to the target user.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for customizable machine learning models. In some implementations, data is received, including (i) example data sets and (ii) data specifying one or more criteria to be assessed. A set of multiple models is trained, where each model in the set of models is trained using a training data set comprising a different subset of the example data sets. Output of the models is obtained for various example data sets, and a combination of n-grams is selected based on the outputs. The example data sets are used to train a classifier to evaluate input data with respect to the specified one or more criteria based on whether the input data includes the n-grams in the selected combination of n-grams.

Abstract: An unsupervised machine learning model can make prediction on time series data. Variance of time-varying parameters for independent variables of the model may be restricted for continuous consecutive time intervals to minimize overfitting. The model may be used in a control system to control other devices or systems. If predictions for the control system are for a higher granularity time interval than the current mode, the time-varying parameters of the model are modified for the higher granularity time interval.

Abstract: Mathematical technologies for recommending content to a user based on a user's preferences are disclosed. Embodiments of these technologies can generate a probabilistic representation of a data set, and then adjust the probabilistic representation to reflect a user-specific weighting scheme. The user preference-adjusted representation of the data set can be used to recommend content to the user.

Abstract: Embodiments associate a relevant semantic data type (e.g., date) with incoming raw data (e.g., a column of digits) which lacks metadata. Assignment of semantic data type is inferred from a plurality of features. A first step determines a first feature comprising success rate in converting the raw data into various semantic data types. Then, alignment between observed/reference distributions of other features (e.g., data first digit, data length) is determined per-semantic data type. Total scores for each semantic data type are calculated from the combined features, and used as a basis for ranking the semantic data types. The total scores may reflect a weighting of the various features. In a second step, top-ranked semantic data types may be further differentiated from one another by applying additional features. User feedback regarding accuracy of semantic data type assignment, may be incorporated into training data used to modify the feature reference distributions.

Abstract: A computing device automatically classifies an observation vector. A label set defines permissible values for a target variable. Supervised data includes a labeled subset that has one of the permissible values. A converged classification matrix is computed based on the supervised data and an unlabeled subset using a prior class distribution matrix that includes a row for each observation vector. Each column is associated with a single permissible value of the label set. A cell value in each column is a likelihood that each associated permissible value of the label set occurs based on prior class distribution information. The value of the target variable is selected using the converged classification matrix. A weighted classification label distribution matrix is computed from the converged classification matrix. The value of the target variable for each observation vector of the plurality of observation vectors is output to a labeled dataset.

Abstract: The current disclosure generally relates to database management systems (DBMSs) and may be generally directed to methods and systems of using artificial intelligence (i.e. machine learning and/or anticipation functionalities, etc.) to learn a user's use of a DBMS, store this “knowledge” in a knowledgebase, and anticipate the user's future operating intentions. The current disclosure may also be generally directed to associative methods and systems of constructing DBMS commands. The current disclosure may also be generally directed to methods and systems of using a simplified DBMS command language (SDCL) for associative DBMS command construction. The current disclosure may also be generally directed to artificially intelligent methods and systems for associative DBMS command construction. The current disclosure may also be generally directed to methods and systems for associative DBMS command construction through voice input.