Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating sequences of predicted observations, for example images. In one aspect, a system comprises a controller recurrent neural network, and a decoder neural network to process a set of latent variables to generate an observation. An external memory and a memory interface subsystem is configured to, for each of a plurality of time steps, receive an updated hidden state from the controller, generate a memory context vector by reading data from the external memory using the updated hidden state, determine a set of latent variables from the memory context vector, generate a predicted observation by providing the set of latent variables to the decoder neural network, write data to the external memory using the latent variables, the updated hidden state, or both, and generate a controller input for a subsequent time step from the latent variables.

Abstract: Embodiments of a method are disclosed. The method includes performing distributed deep learning training on multiple batches of training data using corresponding learners. Additionally, the method includes determining training times wherein the learners perform the distributed deep learning training on the batches of training data. The method also includes modifying a processing aspect of the straggler to reduce a future training time of the straggler for performing the distributed deep learning training on a new batch of training data in response to identifying a straggler of the learners by a centralized control.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing a compressed recurrent neural network (RNN). One of the systems includes a compressed RNN, the compressed RNN comprising a plurality of recurrent layers, wherein each of the recurrent layers has a respective recurrent weight matrix and a respective inter-layer weight matrix, and wherein at least one of recurrent layers is compressed such that a respective recurrent weight matrix of the compressed layer is defined by a first compressed weight matrix and a projection matrix and a respective inter-layer weight matrix of the compressed layer is defined by a second compressed weight matrix and the projection matrix.

Abstract: An abduction apparatus 1 includes: a probability calculation unit 2 configured to, with respect to each of candidate hypotheses generated using observation information and knowledge information, calculate a probability that the candidate hypothesis holds true as an explanation of the observation information; and a reward selection unit 3 configured to, when the candidate hypothesis holds true, select a reward value regarding the candidate hypothesis that has held true by referring to reward definition information in which a condition that the candidate hypothesis holds true is associated with the reward value.

Abstract: In an approach to improve the efficiency of solving problem instances by utilizing a machine learning model to solve a sequential optimization problem. Embodiments of the present invention receive a sequential optimization problem for solving and utilize a random initialization to solve a first instance of the sequential optimization problem. Embodiments of the present invention learning, by a computing device a machine learning model, based on a previously stored solution to the first instance of the sequential optimization problem. Additionally, embodiments of the present invention generate, by the machine learning model, one or more subsequent approximate solutions to the sequential optimization problem; and output, by a user interface on the computing device, the one or more subsequent approximate solutions to the sequential optimization problem.

Abstract: Methods, systems, and apparatus for solving computational tasks using quantum computing resources. In one aspect a method includes receiving, at a quantum formulation solver, data representing a computational task to be performed; deriving, by the quantum formulation solver, a formulation of the data representing the computational task that is formulated for a selected type of quantum computing resource; routing, by the quantum formulation solver, the formulation of the data representing the computational task to a quantum computing resource of the selected type to obtain data representing a solution to the computational task; generating, at the quantum formulation solver, output data including data representing a solution to the computational task; and receiving, at a broker, the output data and generating one or more actions to be taken based on the output data.

Abstract: A system and method for using a deep learning model to learn program semantics is disclosed. The method includes receiving a plurality of execution traces of a program, each execution trace comprising a plurality of variable values. The plurality of variable values are encoded by a first recurrent neural network to generate a plurality of program states for each execution trace. A bi-directional recurrent neural network can then determine a reduced set of program states for each execution trace from the plurality of program states. The reduced set of program states are then encoded by a second recurrent neural network to generate a plurality of executions for the program. The method then includes pooling the plurality of executions to generate a program embedding and predicting semantics of the program using the program embedding.

Abstract: The invention relates generally to a system and method for integrating pet health records, and more specifically to an integrated pet health record that is configured to collect, store, maintain, analyze, and provide recommendations about a pet's health from a variety of sources. The system may analyze health conditions for a pet on both an individual basis and in regards to a global population. This analysis provides an assessment of the pet based on pet type, breed, age, weight, geographic location, living conditions, diet, exercise, and more. The system may also generate global statistics, providing various metrics that can be applied to sub-populations of pets. Advantageously, the system is configured to categorize causes and symptoms based on the pet's health conditions and how treatments can be refined to improve outcomes, and transmit that information to a client device.

Abstract: The invention relates generally to a system and method for animal health decision support, and more specifically to a non-human animal health decision support system that is configured to collect animal information, determine a health topic, and transmit a question set corresponding to the health topic. The system may analyze answers associated with the question set to determine a course of action. The course of action may be a recommendation, such as contacting a veterinarian, obtaining a relevant product, making an appointment with a veterinarian, watching for change in symptoms in the non-human animal, and transporting the non-human animal to a clinic. Advantageously, the system is configured to provide decision support and transmit that information to a client device.

Abstract: In a general aspect, a method executed in a quantum computing system includes performing a calibration process in the quantum computing system to identify a value of a parameter of the quantum computing system. The method also includes analyzing a variation of the value in response to a change in a condition of the quantum computing system, thereby determining a stability of the parameter. The method additionally includes scheduling a recalibration of the parameter based on the stability of the parameter and executing a quantum algorithm in the quantum computing system based on the value of the parameter identified by the calibration process.

Abstract: A method comprises receiving a network of a plurality of nodes and a plurality of edges, each of the nodes comprising members representative of at least one subset of training data points, each of the edges connecting nodes that share at least one data point, grouping the data points into a plurality of groups, each data point being a member of at least one group, creating a first transformation data set, the first transformation data set including the training data set as well as a plurality of feature subsets associated with at least one group, values of a particular data point for a particular feature subset for a particular group being based on values of the particular data point if the particular data point is a member of the particular group, and applying a machine learning model to the first transformation data set to generate a prediction model.

Abstract: A social networking application provides for automated link and/or content recommendation to users of a social media platform by automated social graph refinement that augments a baseline social graph with predicted links and inferred labels by iteratively (a) propagating attribute labels through optimizing attribute label similarity between user nodes constrained by closeness of links between the users, and (b) predicting links between users through optimizing link closeness constrained by label similarity. Each label inference iteration is based on predicted labels generated in and immediately prior link prediction iteration, and each link prediction iteration is based on inferred labels generated in and immediately prior label inference iteration.

Abstract: Systems and methods for training a conditional generator model are described. Methods receive a sample, and determine a discriminator loss for the received sample. The discriminator loss is based on an ability to determine whether the sample is generated by the conditional generator model or is a ground truth sample. The method determines a secondary loss for the generated sample and updates the conditional generator model based on an aggregate of the discriminator loss and the secondary loss.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for receiving a request from a client to process a computational graph; obtaining data representing the computational graph, the computational graph comprising a plurality of nodes and directed edges, wherein each node represents a respective operation, wherein each directed edge connects a respective first node to a respective second node that represents an operation that receives, as input, an output of an operation represented by the respective first node; identifying a plurality of available devices for performing the requested operation; partitioning the computational graph into a plurality of subgraphs, each subgraph comprising one or more nodes in the computational graph; and assigning, for each subgraph, the operations represented by the one or more nodes in the subgraph to a respective available device in the plurality of available devices for operation.

Abstract: A method, system and computer-usable medium for providing cognitive insights comprising receiving data from a plurality of data sources, the plurality of data sources comprising a blockchain data source, the blockchain data source providing blockchain data; processing the data from the plurality of data sources, the processing the data from the plurality of data sources performing data enriching to provide enriched data; generating the cognitive session graph, the cognitive session graph being associated with a session, the cognitive session graph comprising at least some enriched data; and, associating a cognitive blockchain with the cognitive session graph.

Abstract: Computer network architectures for machine learning, and more specifically, computer network architectures for the automated completion of healthcare claims. Embodiments of the present invention provide computer network architectures for the automated completion of estimated final cost data for claims for healthcare clinical episodes using incomplete data for healthcare insurance claims and costs, known to date. Embodiments may use an automatic claims completion web application, with other computer network architecture components. Embodiments may include a combination of third-party databases to generate estimated final claims for pending patient clinical episodes, and to drive the forecasting models for the same, including social media data, financial data, social-economic data, medical data, search engine data, e-commerce site data, and other databases.

Abstract: A machine learning system includes a learning section and an operating section including a memory. The operating section holds a required accuracy, and an internal state and a weight value of a learner in the memory and executes calculation processing by using data input to the machine learning system and the weight value held in the memory to update the internal state. An accuracy of the internal state is calculated from a result of the calculation processing and an evaluation value is calculated using the data input to the machine learning system, the weight value, and the updated internal state held in the memory when the calculated accuracy is higher than the required accuracy. The evaluation value is transmitted to the learning section, which updates the weight value by using the evaluation value and notifies the number of times of updating the weight value to the operating section.

Abstract: An information processing method includes acquiring first output data for input data of first learning model, reference data for the input data, and second output data for the input data of second learning model obtained by converting first learning model; calculating first difference data corresponding to a difference between the first difference data and the reference data and second difference data corresponding to a difference between the second output data and the reference data; and training first learning model with use of the first difference data and the second difference data.

Abstract: A method of generating a question-answer learning model through adversarial learning may include: sampling a latent variable based on constraints in an input passage; generating an answer based on the latent variable; generating a question based on the answer; and machine-learning the question-answer learning model using a dataset of the generated question and answer, wherein the constraints are controlled so that the latent variable is present in a data manifold while increasing a loss of the question-answer learning model.

Abstract: A first and second blending profile may be created for a set of question answering pipelines. A set of test answer data may be generated for a first answering pipeline. The test answer data may be generated based on a set of test question and using an answer key associated with the test questions. Based on the test answer data, a first blending profile can be created for the first answering pipeline. Using the set of test questions and a second answer key, another set of test answer data may be generated. This set may be generated for the second answering pipeline. Using this second answering pipeline test answer data, a second blending profile can be generated for the second answering pipeline. Each blending profile may have metadata about a confidence of each pipeline.