Abstract: The subject disclosure relates to systems for managing the deployment and updating of incremental machine learning models across multiple geographic sovereignties. In some aspects, systems of the subject technology are configured to perform operations including: receiving a first machine learning model via a first coordination agent, the first machine learning model based on a first training data set corresponding with a first sovereign region, sending the first machine learning model to a second coordination agent in a second sovereign region, wherein the second sovereign region is different from the first sovereign region, and receiving a second machine learning model from the second coordination agent, wherein the second machine learning model is based on updates to the first machine learning model using a second training data set corresponding with the second sovereign region. Methods and machine-readable media are also provided.

Abstract: A method for implementing a convolutional neural network (CNN) accelerator on a target includes utilizing one or more processing elements to implement a standard convolution layer. A configuration of the CNN accelerator is modified to change a data flow between components on the CNN accelerator. The one or more processing elements is utilized to implement a fully connected layer in response to the change in the data flow.

Abstract: Disclosed herein is a computer-implemented tool that facilitates data analysis by use of machine learning (ML) techniques. The tool cooperates with a data intake and query system and provides a graphical user interface (GUI) that enables a user to train and apply a variety of different ML models on user-selected datasets of stored machine data. The tool can provide active guidance to the user, to help the user choose data analysis paths that are likely to produce useful results and to avoid data analysis paths that are less likely to produce useful results.

Abstract: An answer to a question may selected from answers from a set of answering pipelines. Question answer data can be generated for a question, using a first answering pipeline. Another set of question answer data can be generated for the second question, using the second answering pipeline. The question answer data can include answers and confidence values for each answer. Using a weighting formula and a blending profile for the first answering pipeline, a vote weight can be determined for an answer with the highest confidence value. The same weighting formula and a second blending profile may be used to determine a vote weight for another answer with the highest confidence value. An answer to the question may be selected from the answers, based on the overall highest vote weight.

Abstract: In one embodiment, a system may access a graph data structure that includes nodes and connections between the nodes. Each node may be associated with a user; each connection between two nodes may represent a relationship between the associated users; and each node may be either labeled or unlabeled with respect to a label type. For each labeled node, a label of the label type of that labeled node may be propagated to other nodes through the connections. For each node, the system may store a label distribution information associated with the label type based on the propagated labels reaching the node. The system may train a machine-learning model using the labels and the label distribution information of a set of the labeled nodes. A predicted label for each unlabeled node may be generated using the model and the label distribution information of the unlabeled node.

Abstract: For a content item with unknown tasks performed by a viewing user on an online system, the online system receives a plurality of content items associated with a viewing user. The online system derives a feature vector for each content item. The online system predicts a likelihood of interacting with each content item using a prediction model associated with a plurality of tasks. The prediction model comprises a plurality of shared layers and a plurality of separate layers. The plurality of shared layers are configured to extract common features that are shared across the plurality of tasks. Each separate layer is configured to predict likelihood of the viewing user performing a task associated with the separate layer based on the common features. The online system scores each content item based on predicted likelihood of each task. The online system ranks the plurality of content items based on the scoring.

Abstract: Systems for distributed data storage. A method embodiment commences upon capturing a history of storage I/O activity over a recent time period. A predictive model is derived from the captured storage I/O activity, and the predictive model is then used for predicting future storage I/O activity. A set of snapshot planning parameters comprising objectives (e.g., to minimize costs or to maximize likelihood completing a snapshot activity by a prescribed time) and/or constraints (e.g., don't wait more than one day to start a snapshot) are applied to the predicted storage I/O characteristics to generate a set of feasible snapshot plans. One of the feasible snapshot plans is selected for scheduling so as to begin the planned snapshot activity at a prescribed time. The snapshot planning parameters are normalized based on the predicted storage I/O characteristics.

Abstract: Components of language processing engines, such as translation models and language models, can be customized for groups of users or based on user type values. Users can be organized into groups or assigned a value on a continuum based on factors such as interests, biographical characteristics, social media interactions, etc. In some implementations, translation engine components can be customized for groups of users by selecting the training data from content created by users in that group. In some implementations, the group identifier or continuum value can be part of the input into a general translation component allowing the translation component to take a language style of that user group into account when performing language processing tasks.

Abstract: A method for providing an interactive infrastructure management system based on a chat interface is provided. The method may include receiving a first operation query via a first infrastructure management chat interface associated with an infrastructure management system. The method may include providing first data instructions using the first infrastructure management chat interface in response to the first operation query. The method may include generating a second infrastructure management chat interface associated with the infrastructure management system to edit and train the infrastructure management system based on the provided first data instructions. The method may include editing the provided first data instructions associated with the first operation query to train the infrastructure management system to respond to the first operation query.

Abstract: Components of language processing engines, such as translation models and language models, can be customized for groups of users or based on user type values. Users can be organized into groups or assigned a value on a continuum based on factors such as interests, biographical characteristics, social media interactions, etc. In some implementations, translation engine components can be customized for groups of users by selecting the training data from content created by users in that group. In some implementations, the group identifier or continuum value can be part of the input into a general translation component allowing the translation component to take a language style of that user group into account when performing language processing tasks.

Abstract: A computing server may use one or more recommender systems to predict phenotypes of individuals based on survey responses, other phenotypes, environmental factors, and genetic data of the individuals. The computing server may retrieve survey responses of a set of individuals regarding a set of phenotypes of the individuals. The computing server may construct a matrix that includes the values of the phenotypes. The computing server may predict an undetermined phenotype of a target individual using collaborative filtering, which provides the prediction based on other phenotypes of the target individuals and based on at least another individual's phenotypes. The computing server may also predict a target phenotype based on the phenotype of other individuals who are similar to the target individual. The computing server may determine another individual is similar to the target individual based on the length of identity-by-descent (IBD) segments between the two individuals.

Abstract: A method, computer program product, and system perform computations using a processor. A first instruction including a first index vector operand and a second index vector operand is received and the first index vector operand is decoded to produce first coordinate sets for a first array, each first coordinate set including at least a first coordinate and a second coordinate of a position of a non-zero element in the first array. The second index vector operand is decoded to produce second coordinate sets for a second array, each second coordinate set including at least a third coordinate and a fourth coordinate of a position of a non-zero element in the second array. The first coordinate sets are summed with the second coordinate sets to produce output coordinate sets and the output coordinate sets are converted into a set of linear indices.

Abstract: Systems and methods for training a neural network or an ensemble of neural networks are described. A hyper-parameter that controls the variance of the ensemble predictors is used to address overfitting. For larger values of the hyper-parameter, the predictions from the ensemble have more variance, so there is less overfitting. This technique can be applied to ensemble learning with various cost functions, structures and parameter sharing. A cost function is provided and a set of techniques for learning are described.

Abstract: In order to compare high-dimensional, multi-modal data for a patient to data for other patients, deep learning is used to encode original, multi-modal data for a patient into a compact signature. The compact signature is compared to predetermined compact signatures generated for other patients, and similar predetermined compact signatures are identified based on the comparison. A clinical outcome may be predicted based on the similar predetermined compact signatures that are identified.

Abstract: Embodiments of the invention are directed to methods and devices for predicting interactions. One embodiment is directed to a method comprising receiving, by one or more computers, interaction data for a plurality of known interactions between resource providers and users, and creating a topological graph based on the plurality of known interactions. The method may further comprise determining, by the one or more computers, a plurality of communities to form a predictive model, and receiving a request for a prediction. In addition, the method may comprise applying the request to the predictive model, by the one or more computers, by identifying a community in the plurality of communities corresponding to the request, determining a node within the identified community, and providing information regarding the node as the requested prediction.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media directed at transforming event logs into features for use in machine learning. In embodiments, a method may include receiving an event log for a user. The event log can indicate an occurrence of a first event associated with the user. The method can also include generating a feature value for the first event. The feature value can be indicative of an amount of time that has passed since the occurrence of the first event. Based, at least in part, on the feature value, an occurrence of a second event can be predicted utilizing a predictive model. The prediction can then be output to enable targeted content associated with the second event to be delivered to the user. Other embodiments may be described and/or claimed herein.

Abstract: A method, computer program product, and system perform computations using a sparse convolutional neural network accelerator. A first vector comprising only non-zero weight values and first associated positions of the non-zero weight values within a 3D space is received. A second vector comprising only non-zero input activation values and second associated positions of the non-zero input activation values within a 2D space is received. The non-zero weight values are multiplied with the non-zero input activation values, within a multiplier array, to produce a third vector of products. The first associated positions are combined with the second associated positions to produce a fourth vector of positions, where each position in the fourth vector is associated with a respective product in the third vector. The products in the third vector are transmitted to adders in an accumulator array, based on the position associated with each one of the products.

Abstract: To make predictions about racing, a point to pay attention to in pre-race movements of each racer can be presented. To this end, for racers entered in a race to be processed, a plurality of captured pre-race movement images of pre-race movements made by the racers before a race are retrieved. By using the retrieved pre-race movement images and racing result information corresponding to each pre-race movement image, an attention point to be paid attention to while each racer is making pre-race movements are identified. Presentation information for presenting information about the identified attention point is then generated and controlled to be presented to a user on an external terminal.

Abstract: A decision tree generating apparatus includes an information gain calculator and a decision tree generator. When a classification target data set including a plurality of pieces of classification target data respectively having different attributes with attribute values assigned thereto is segmented into subsets in a form of a decision tree, the information gain calculator calculates an amount of entropy reduction on each attribute, and calculates an information gain, based on the amount of reduction in the entropy and reliability of a user's answer responsive to an inquiry asking about the attribute. The decision tree generator successively determines an attribute having a maximum information gain to be a node of the decision tree by recursively iterating the segmentation of the pre-segmentation data set, and generates the decision tree that is to be used to determine an order of the inquiries.

Abstract: Generally discussed herein are devices, systems, and methods for encoding input-output examples. A method of generating a program using an encoding of input-output examples, may include processing an input example of the input-output examples, using a first long short term memory (LSTM) neural network, one character at a time to produce an input feature vector, processing an output example associated with the input example in the input-output examples, using the LSTM neural network, one character at a time to produce an output feature vector, determining (a) a cross-correlation between the input feature vector and the output feature vector or (b) previously computed feature vectors for a different input-output example that are sufficiently close to the input feature vector and the output feature vector, respectively, and using the determined cross-correlation or previously computed vector, generating a program consistent with the input example and the output example.