Abstract: A method includes receiving input that identifies one or more data sources and determining, based on the input, a machine learning problem type of a plurality of machine learning problem types supported by an automated model building (AMB) engine. The method also includes generating an input data set of the AMB engine based on application of one or more rules to the one or more data sources. The method further includes, based on the input data set and the machine learning problem type, initiating execution of the AMB engine to generate a neural network configured to model at least a portion of the input data set.

Abstract: A method includes performing, by a computing device, a clustering operation to group documents of a document corpus into clusters in a feature vector space. The document corpus includes one or more labeled documents and one or more unlabeled documents. Each of the one or more labeled documents is assigned to a corresponding class in classification data associated with the document corpus, and each of the one or more unlabeled document is not assigned to any class in the classification data. The method also includes generating, by the computing device, a prompt requesting classification of a particular document of the document corpus, where the particular document is selected based on a distance between the particular document and a labeled document of the one or more labeled documents.

Abstract: A method of generating a neural network includes iteratively performing operations including generating, for each neural network of a population, a matrix representation. The matrix representation of a particular neural network includes rows of values, where each row corresponds to a set of layers of the particular neural network and each value specifies a hyperparameter of the set of layers. The operations also include providing the matrix representations as input to a relative fitness estimator that is trained to generate estimated fitness data for neural networks of the population. The estimated fitness data are based on expected fitness of neural networks predicted by the relative fitness estimator. The operations further include generating, based on the estimated fitness data, a subsequent population of neural networks. The method also includes, when a termination condition is satisfied, outputting data identifying a neural network as a candidate neural network.

Abstract: A method includes receiving input designating a term of interest in a document of a document corpus and determining a target context embedding representing a target word group that includes the term of interest and context words located in the document proximate to the term of interest. The method also includes identifying, from among the document corpus, a first candidate word group that is semantically similar to the target word group and a second candidate word group that is semantically dissimilar to the target word group. The method further includes receiving user input identifying at least a portion of the first candidate word group as associated with a first label and identifying at least a portion of the second candidate word group as not associated with the first label. The method also includes generating labeled training data based on the user input to train a text classifier.

Abstract: A method includes receiving, via a graphical user interface including a plurality of document elements and a plurality of class elements, user input associating a first document element of the plurality of document elements with a first class element of the plurality of class elements. Each document element represents a corresponding document of a plurality of documents, and each class element represents a corresponding class of a plurality of classes. The method also includes generating a document classifier using supervised training data, where the supervised training data indicates, based on the user input, that a first document represented by the first document element is assigned to a first class associated with the first class element.

Abstract: A method includes, during an epoch of a genetic algorithm, determining a fitness value for each of a plurality of autoencoders. The fitness value for an autoencoder indicates reconstruction error responsive to data representing a first operational state of one or more devices. The method includes selecting, based on the fitness values, a subset of autoencoders. The method also includes performing a genetic operation with respect to at least one autoencoder to generate a trainable autoencoder. The method includes training the trainable autoencoder to reduce a loss function value to generate a trained autoencoder. The loss function value is based on reconstruction error of the trainable autoencoder responsive to data representative of a second operational state of the device(s). The method includes adding the trained autoencoder to a population to be provided as input to a subsequent epoch of the genetic algorithm.

Abstract: A method includes determining a feature importance ranking for each pair of clusters of a plurality of clusters to generate a first plurality of feature importance rankings. The method further includes determining a feature importance ranking between a particular data element and each cluster to generate a second plurality of feature importance rankings. A distance value associated with each pair of clusters of the plurality of clusters is determined to generate a plurality of distance values, and a probability value associated with each data element is determined to generate a plurality of probability values. The method further includes weighting the first plurality of feature importance rankings based on the plurality of distance values to determine a first plurality of weighted feature importance rankings and weighting the second plurality of feature importance rankings based on the plurality of probability values to determine a second plurality of weighted feature importance rankings.

Abstract: A particular method includes automatically generating, at a processor of a computing device, annotation data indicating that a column of a data table corresponds to a particular class of an ontology. The method also includes storing the annotation data. The method further includes receiving a natural language query. The method also includes generating a second query based on detecting a match between at least one term of the natural language query and the annotation data. The method further includes determining a response to the second query. The method also includes outputting the response to the second query as a response to the natural language query.

Abstract: A method of generating a neural network includes iteratively performing operations including generating, for each neural network of a population, a matrix representation. The matrix representation of a particular neural network includes rows of values, where each row corresponds to a set of layers of the particular neural network and each value specifies a hyperparameter of the set of layers. The operations also include providing the matrix representations as input to a relative fitness estimator that is trained to generate estimated fitness data for neural networks of the population. The estimated fitness data are based on expected fitness of neural networks predicted by the relative fitness estimator. The operations further include generating, based on the estimated fitness data, a subsequent population of neural networks. The method also includes, when a termination condition is satisfied, outputting data identifying a neural network as a candidate neural network.

Abstract: A method includes receiving, by a processor, an input data set. The input data set includes a plurality of features. The method includes determining, by the processor, one or more characteristics of the input data set. The method includes, based on the one or more characteristics, adjusting, by the processor, one or more architectural parameters of an automated model generation process. The automated model generation process is configured to generate a plurality of models using a weighted randomization process. The one or more architectural parameters weight the weighted randomization process to adjust a probability of generation of models having particular architectural features. The method further includes executing, by the processor, the automated model generation process to output a mode, the model including data representative of a neural network.

Abstract: A method includes determining, by a processor of a computing device, a subset of models included in a plurality of models generated based on a genetic algorithm and corresponds to a first epoch of the genetic algorithm. Each of the plurality of models includes data representative of a neural network. The method includes aggregating the subset of models to generate an ensembler. The ensembler, when executed on an input, provides at least a portion of the input to each model of the subset of models to generate a plurality of intermediate outputs. An ensembler output of the ensembler is based on the plurality of intermediate outputs. The method further includes executing the ensembler on input data to determine the ensembler output.

Abstract: Automated malware detection for application file packages using machine learning (e.g., trained neural network-based classifiers) is described. A particular method includes generating, at a first device, a first feature vector based on occurrences of character n-grams corresponding to a first subset of files of multiple files of an application file package. The method includes generating, at the first device, a second feature vector based on occurrences of attributes in a second subset of files of the multiple files. The method includes sending the first feature vector and the second feature vector from the first device to a second device as inputs to a file classifier. The method includes receiving, at the first device from the second device, classification data associated with the application file package based on the first feature vector and the second feature vector. The classification data indicates whether the application file package includes malware.

Abstract: A method includes receiving a first file attribute from a computing device. The method also includes determining whether a classification for a file is available from a first cache of the server based on the first file attribute. The method includes sending the first file attribute from the server to a second server to determine whether the classification for the file is available at a base prediction cache of the second server. The method includes receiving a notification at the server from the second server that the classification for the file is unavailable at the base prediction cache. The method includes, in response to receiving the notification, determining the classification for the file by performing an analysis of a second file attribute based on a trained file classification model. The method includes sending the classification to the computing device and sending at least the classification to the base prediction cache.

Abstract: A method includes determining, by a processor of a computing device, an expected performance or reliability of a first neural network of a first plurality of neural networks. The expected performance or reliability is determined based on a vector representing at least a portion of the first neural network, where the first neural network is generated based on an automated generative technique (e.g., a genetic algorithm) and where the first plurality of neural networks corresponds to a first epoch of the automated generative technique. The method also includes responsive to the expected performance or reliability of the first neural network failing to satisfy a threshold, adjusting a parameter of the automated generative technique. The method further includes, during a second epoch of the automated generative technique, generating a second plurality of neural networks based at least in part on the adjusted parameter.

Abstract: An aspect of the present invention is to provide a system and method for predicting the remaining useful time of mechanical components such as bearings. Another aspect of the present invention is to provide a system and method for predicting the remaining useful time of bearings based on available condition monitoring data. Another aspect of the present invention is to provide a system and method for automatically deciding which columns of input information are the most significant for predicting the remaining useful life of bearings. Another aspect of the present invention is to provide a system and method for performing an analysis of both test bearings and training bearings and determining which training bearings are most similar to a given test bearing. Another aspect of the present invention is to provide a system and method for training an artificial neural network.

Abstract: A computer system includes a memory storing a data structure representing a neural network. The data structure includes a plurality of fields including values representing topology of the neural network. The computer system also includes one or more processors configured to perform neural network classification by operations including generating a vector representing at least a portion of the neural network based on the data structure. The operations also include providing the vector as input to a trained classifier to generate a classification result associated with at least the portion of the neural network, where the classification result is indicative of expected performance or reliability of the neural network. The operations also include generating an output indicative of the classification result.

Abstract: A method includes receiving an input data set, each entry including multiple features. The method includes receiving a user input identifying a target feature of the multiple features and a target value of the target feature. The method includes determining, one or more correlated features of the multiple features. The method includes providing the input data set to multiple neural networks (including multiple VAEs) to train the multiple neural networks. The method includes generating a simulated data set based on the input data set, each entry including at least the target feature and the one or more correlated features. Values of the one or more correlated features are randomized or pseudorandomized and the target feature is fixed at the target value. The method includes providing the simulated data set to the multiple neural networks to generate output data and displaying a GUI based on the output data.

Abstract: During training mode, first input data is provided to a first neural network to generate first output data indicating that the first input data is classified in a first cluster. The first input data includes at least one of a continuous feature or a categorical feature. Second input data is generated and provided to at least one second neural network to generate second output data. The at least one second neural network corresponds to a variational autoencoder. An aggregate loss corresponding to the second output data is determined, including at least one of evaluating a first loss function for the continuous feature or evaluating a second loss function for the categorical feature. Based on the aggregate loss, at least one parameter of at least one neural network is adjusted. During use mode, the neural networks are used to determine cluster identifications and anomaly likelihoods for received data samples.

Abstract: An unmanned aerial vehicle (UAV) system comprises a hangar structure configurable to mount on a host platform. The hangar structure comprises electrical circuits comprising a charging circuit and a communications circuit. The UAV system further comprises a plurality of stackable UAVs. The plurality of stackable UAVs comprise respective batteries and control circuits. The plurality of stackable UAVs are configured to cooperate with the charging circuit to charge the batteries and to cooperate with the communications circuit to communicate with the control circuits while the plurality of stackable UAVs are in a stacked configuration within the hangar structure.

Abstract: A method includes receiving, at a server, a first file attribute from a computing device, the first file attribute associated with a file. The method also includes determining, based on the first file attribute, that a classification for the file is unavailable. The method further includes determining the classification for the file based on a trained file classification model accessible to the server and sending the classification to the computing device. The method includes sending at least the classification to a base prediction cache associated with a second server.