Abstract: A computer-implemented method is provided for training a classification model. The method includes preparing, by a processor, positive and negative class data. The method further includes iteratively training the classification model, by the processor, using the positive class data and the negative class data such that the positive class data is reconstructed and the negative class data is prevented from being constructed, by the classification model. In response to a selection of a non-integer value as a number of negative learning iterations to be performed to train the classification model, a particular set of the negative class data that is reconstructed best by the classification model from among all of the negative class data is selected to be used for negative learning by the classification model. The training based on the positive class data is performed once before the negative learning iterations and once after each negative learning iteration.

Abstract: A computer-implemented method is provided for training a classification model. The method includes preparing, by a processor, positive and negative class data. The method further includes iteratively training the classification model, by the processor, using the positive class data and the negative class data such that the positive class data is reconstructed and the negative class data is prevented from being constructed, by the classification model. In response to a selection of a non-integer value as a number of negative learning iterations to be performed to train the classification model, a particular set of the negative class data that is reconstructed best by the classification model from among all of the negative class data is selected to be used for negative learning by the classification model. The training based on the positive class data is performed once before the negative learning iterations and once after each negative learning iteration.

Abstract: A first set of garbage collection (GC) features and non-GC features associated with a storage system are received, the first set of features being associated with a predetermined start date and a time window. A learning equation is generated having a plurality of vectors of GC features and a plurality of vectors of non-GC features. For a current iteration representing a current GC process, it is determined whether a first prior GC process was started within the time window. An entry of vectors of the non-GC features of the learning equation is populated based on corresponding feature values of the first set of non-GC features, in response to determining that the first prior GC process was started within the time window. A predetermined regression algorithm is applied to the learning equation to generate a GC duration predictive model to predict a GC duration of a subsequent GC process.

Abstract: Embodiments of the invention relate to canonical spiking neurons for spatiotemporal associative memory. An aspect of the invention provides a spatiotemporal associative memory including a plurality of electronic neurons having a layered neural net relationship with directional synaptic connectivity. The plurality of electronic neurons configured to detect the presence of a spatiotemporal pattern in a real-time data stream, and extract the spatiotemporal pattern. The plurality of electronic neurons are further configured to, based on learning rules, store the spatiotemporal pattern in the plurality of electronic neurons, and upon being presented with a version of the spatiotemporal pattern, retrieve the stored spatiotemporal pattern.

Abstract: Embodiments of the present invention relate to knowledge representation systems which include a knowledge base in which knowledge is represented in a structured, machine-readable format that encodes meaning. Techniques for extracting structured knowledge from unstructured text and for determining the reliability of such extracted knowledge are also described.

Abstract: One embodiment provides a system for generating an inference model that determines an activity type for a user from contextual information. During operation, the system receives a set of contextual information associated with the user, wherein the contextual information includes at least a set of location coordinates. The system then determines an association between the contextual information and an activity type. Next, the system generates an activity inference model based in part on the association, wherein the activity inference model takes an instance of contextual information as an input parameter and outputs a corresponding activity type. The model's parameters are based at least on statistics associated with the user's contextual history but not based on the complete contents of the user's contextual history.

Abstract: A method for generating hypotheses in a corpus of data comprises selecting a form of ontology; coding the corpus of data based on the form of the ontology; generating ontology space based on coding results and the ontology; transforming the ontology space into a hypothesis space by grouping hypotheses; weighing hypotheses included in the hypothesis space; and applying a science-based optimization algorithm configured to model a science-based treatment of the weighted hypotheses.

Abstract: Systems and methods for defining a custom segment in a set of behavioral data are provided. A described method includes receiving a set of behavioral data associated with a plurality of user devices and identifying multiple cohort groups, each of the cohort groups including one or more of the user devices. The behavioral data includes a behavior metric for each of the user devices and the cohort groups are identified based on the behavior metric for each of the user devices. The method further comprises generating a segmentation interface including a graphical visualization of the multiple cohort groups and causing the segmentation interface to be presented via a user interface device. The method further comprises defining a custom segment of the behavioral data based on a user selection of one or more of the multiple cohort groups via the segmentation interface.

Abstract: Optimized learning settings of neural networks are efficiently determined by an apparatus including a processor and one or more computer readable mediums collectively including instructions that, when executed by the processor, cause the processor to train a first neural network with a learning setting; extract tentative weight data from the first neural network with the learning setting; calculate an evaluation value of the first neural network with the learning setting; and generate a predictive model for predicting an evaluation value of a second neural network with a new setting based on tentative weight data of the second neural network by using a relationship between the tentative weight data of the first neural network and the evaluation value of the first neural network.

Abstract: Embodiments of the invention relate to providing transposable access to a synapse array using a recursive array layout. One embodiment comprises maintaining synaptic weights for multiple synapses connecting multiple axons and multiple neurons, wherein the synaptic weights are maintained based on a recursive array layout. The recursive array layout facilitates transposable access to the synaptic weights. A neuronal spike event between an axon and a neuron is communicated via a corresponding connecting synapse by accessing the synaptic weight of the corresponding connecting synapse in the recursive array layout.

Abstract: Systems and methods for efficiently detecting and coordinating step changes, trends, cycles, and bursts affecting lexical items within data streams are provided. Data streams can be sourced from documents that can optionally be labeled with metadata. Changes can be grouped across lexical and/or metavalue vocabularies to summarize the changes that are synchronous in time. The methods described herein can be applied either retrospectively to a corpus of data or in a streaming mode.

Abstract: Systems and methods for implementing an artificially intelligent virtual assistant includes collecting a user query; using a competency classification machine learning model to generate a competency label for the user query; using a slot identification machine learning model to segment the text of the query and label each of the slots of the query; generating a slot value for each of the slots of the query; generating a handler for each of the slot values; and using the slot values to: identify an external data source relevant to the user query, fetch user data from the external data source, and apply one or more operations to the query to generate response data; and using the response data, to generate a response to the user query.

Abstract: A classifier is computed as follows. For a first set of values of primary field(s) of primary data instances of a labeled primary training dataset, a second set(s) of secondary fields of unclassified second data instances of secondary dataset(s) is identified. First set of values are matched to corresponding values in respective secondary field(s), and linked to other secondary fields of respective secondary data instance(s) of the respective matched secondary field. A set of classification features is generated. Each including: (i) condition(s), and (ii) a value selected from the linked other secondary fields of the respective secondary data instance(s) of the respective matched secondary field(s). The respective classification feature outputs a binary value computed by the condition(s) that compares between the value selected from the other linked secondary fields and a new received data instance. A classifier is computed according to a selected subset of the classification features.

Abstract: Provided are a computer program product, system, and method for determining real-time changes to content entered into a user interface to generate results for the content. In response to determining that entry of first content in a user input field rendered in a user interface is completed, the first content is provided to a classification program to classify into a first machine classification to provide to a rules engine to determine a first machine determined proposition. The first machine determined proposition is rendered in the user interface. A determination is made of second content in the user input field from the user that differs from the first content. The second content is provided to the classification program to classify into a second machine classification to provide to the rules engine to determine a second machine determined proposition rendered in the user interface with the second content.

Abstract: A learning apparatus and method for learning a model corresponding to time-series input data, comprising: acquire the time-series input data; supply a plurality of input nodes of the model with a plurality of input values corresponding to input data at one time point in the time-series input data; store values of hidden nodes; compute a conditional probability of each input value at the one time point on a condition that an input data sequence has occurred, based on the input data sequence before the one time point in the time-series input data, on the stored values of hidden nodes, and on weight parameters; and perform a learning process that further increases a conditional probability of input data occurring at the one time point on the condition that the input data sequence has occurred, by adjusting the weight parameters.

Abstract: Methods, systems and computer program products for periodically generating a personalized playlist of media objects based on a most recent taste profile of a user. An N-dimensional latent factor vector that defines a taste profile of a user is constructed and matched to an M-dimensional latent factor vector that defines attributes of a media object. A playlist including the first media object is generated based on the matching.

Abstract: A method of performing predictive analysis includes generating, using a computational device, an instance from an unstructured data source. The method further includes associating a variable entity with the instance. The variable entity is associated with an influencer of a set of influencers or a performance indicator of a set of performance indicators. In another example, the method includes determining, using the computational device, a value of the variable entity from the instance based on a value-detection rule and generating, using the computational device, a model associating the set of influencers with the set of performance indicators using the value of the variable entity.

Abstract: Systems, methods, apparatuses, and computer program products to generate, by a computing model, a transformed dataset based on a first dataset comprising numeric values, the computing model to convert the numeric values from a first format to a second format, generate a training dataset comprising the first dataset as an input dataset and the transformed dataset as an output dataset, train an autoencoder comprising a latent vector to transform the input dataset from the first format to the second format, determine, by a statistical model based on an output of the trained autoencoder and the input dataset, an accuracy of the trained autoencoder, and determine that the accuracy of the trained autoencoder exceeds a threshold accuracy.

Abstract: Systems, methods, and computer readable media are disclosed for generating, modifying, and using machine learning models to predict and evaluate differences between groups. Methods disclosed herein may include identifying variables that characterize members of a first group, generating shift indicators using the identified variables, generating a machine learning model using the shift indicators and the first group, using the machine learning model and the group to predict shifts between the first group and a predicted second group, determining an aggregate population shift and an aggregate performance shift between the first group and an actual second group, and identifying an impact of one or more of the shift indicators on the aggregate population shift or performance shift. Systems and methods disclosed herein may be configured to receive requests to predict and evaluate differences between group, and to return such predictions and evaluations to one or more users.

Abstract: A recommendation system generates recommendations for an online system using one or more neural network models that predict preferences of users for items in the online system. The neural network models generate a latent representation of a user and of a user that can be combined to determine the expected preference of the user to the item. By using neural network models, the recommendation system can generate predictions in real-time for new users and items without the need to re-calibrate the models. Moreover, the recommendation system can easily incorporate other forms of information other than preference information to generate improved preference predictions by including the additional information to generate the latent description of the user or item.