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 method includes accessing a structured content item from a first database and event data from a second database, the event data including sets of event attributes in a multi-dimensional namespace and associated with a respective point in time; determining a relevancy profile characterizing a metric of relevancy of the structured content item over a respective time interval, the metric of relevancy including a distance in the multi-dimensional namespace between attributes associated with the structured content and the sets of event attributes; generating, using the relevancy profile, second digital content including a subset of the structured content item; and providing the second digital content for rendering on a device. Related apparatus, systems, techniques and articles are also described.

Abstract: One embodiment can provide a system for detecting anomaly for high-dimensional sensor data associated with one or more machines. During operation, the system can obtain sensor data from a set of sensor associated with one or machines, generate a first set of outputs by using a set of clustering models learned in parallel from the unlabeled sensor data and user-provided partial label information, generate a second set of outputs by using a set of feed-forward neural network (FNN) models learned in parallel from the first set of outputs and the unlabeled sensor data, and determine whether an anomaly is present in the operation of the one or more machines based on the second set of outputs and a user-specified threshold.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating multi-modal data archetypes. In one aspect, a method comprises obtaining a plurality of training examples, wherein each training example corresponds to a respective patient and includes multi-modal data, having a plurality of feature dimensions, that characterizes the patient; jointly training an encoder neural network and a decoder neural network on the plurality of training examples; and generating a plurality of multi-modal data archetypes that each correspond to a respective dimension of a latent space, comprising, for each multi-modal data archetype: processing a predefined embedding that represents the corresponding dimension of the latent space using the decoder neural network to generate multi-modal data, having the plurality of feature dimensions, that defines the multi-modal data archetype.

Abstract: IoT Big Data information management and control systems and methods for distributed performance monitoring and critical network fault detection comprising a combination of capabilities including: IoT data collection sensor stations receiving sensor input signals and also connected to monitor units providing communication with other monitor units and/or cloud computing resources via IoT telecommunication links, and wherein a first data collection sensor station has expert predesignated other network elements comprising other data collection sensor stations, monitor units, and/or telecommunications equipment for performance and/or fault monitoring based on criticality to said first data collection sensor station operations, thereby extending monitoring and control operations to include distributed interdependent or critical operations being monitored and analyzed throughout the IoT network, and wherein performance and/or fault monitoring signals received by said first data collection sensor station are analyzed

Abstract: Described herein are embodiments for question answering over knowledge graph using a Knowledge Embedding based Question Answering (KEQA) framework. Instead of inferring an input questions' head entity and predicate directly, KEQA embodiments target jointly recovering the question's head entity, predicate, and tail entity representations in the KG embedding spaces. In embodiments, a joint distance metric incorporating various loss terms is used to measure distances of a predicated fact to all candidate facts. In embodiments, the fact with the minimum distance is returned as the answer. Embodiments of a joint training strategy are also disclosed for better performance. Performance evaluation on various datasets demonstrates the effectiveness of the disclosed systems and methods using the KEQA framework.

Abstract: A learning method explores, in a block space, a global path from a sub initial point to a sub goal candidate region for movement of an agent, and limits, based on the global path, an exploring space to thereby determine a limited space in the exploring space. The method arranges a sub goal in the limited space in accordance with a position of a goal point, and transforms absolute coordinates of each of at least one obstacle and a sub goal in the limited space into corresponding relative coordinates relative to a position of an agent located in the limited space. Then, the method explores, in the limited space, a target path from the initial point to the sub goal.

Abstract: A computer trains a neural network. A neural network is executed with a weight vector to compute a gradient vector using a batch of observation vectors. Eigenvalues are computed from a Hessian approximation matrix, a regularization parameter value is computed using the gradient vector, the eigenvalues, and a step-size value, a search direction vector is computed using the eigenvalues, the gradient vector, the Hessian approximation matrix, and the regularization parameter value, a reduction ratio value is computed, an updated weight vector is computed from the weight vector, a learning rate value, and the search direction vector or the gradient vector based on the computed reduction ratio value, and an updated Hessian approximation matrix is computed from the Hessian approximation matrix, the predefined learning rate value, and the search direction vector or the gradient vector based on the reduction ratio value. The step-size value is updated using the search direction vector.

Abstract: Embodiments describe an approach for leveraging Bots across various layers of an enterprise information technology system for reducing mean time to find problems (MTFP). The approach comprising: determining if one or more system Bots can identify one or more issues in an enterprise information technology system. Escalating the one or more issues to one or more process Bots. Invoking one or more MTFP computation engines from related Bots in communication with the one or more process Bots. Identifying the one or more issues in the enterprise information technology system by the one or more MTFP computation engines. Updating a knowledge repository with attributes of the identified one or more issues, wherein the one or more process Bots can cognitively learn from the data stored on the knowledge repository; and outputting the one or more identified issues to a user.

Abstract: Functions are added to a deep neural network (“DNN”) computation graph for encoding data structures during a forward training pass of the DNN and decoding previously-encoded data structures during a backward training pass of the DNN. The functions added to the DNN computation graph can be selected based upon on the specific layer pairs specified in the DNN computation graph. Once a modified DNN computation graph has been generated, the DNN can be trained using the modified DNN computation graph. The functions added to the modified DNN computation graph can reduce the utilization of memory during training of the DNN.

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: Certain aspects involve updating data structures to indicate relationships between attribute trends and response variables used for training automated modeling systems. For example, a data structure stores data for training an automated modeling algorithm. The training data includes attribute values for multiple entities over a time period. A computing system generates, for each entity, at least one trend attribute that is a function of a respective time series of attribute values. The computing system modifies the data structure to include the generated trend attributes and updates the training data to include trend attribute values for the trend attributes. The computing system trains the automated modeling algorithm with the trend attribute values from the data structure. In some aspects, trend attributes are generated by applying a frequency transform to a time series of attribute values and selecting, as trend attributes, some of the coefficients generated by the frequency transform.

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: A data processing method and device are provided. The method includes: performing a forward calculation of a neural network on global data to obtain intermediate data for a reverse calculation of the neural network; storing the intermediate data in a buffer unit; reading the intermediate data from the buffer unit; and performing the reverse calculation of the neural network on the intermediate data to obtain a result of the reverse calculation. According to embodiments, in the reverse calculation of the neural network, the number of accessing the global memory is reduced, thereby reducing the computational time cost and increasing the data processing speed.

Abstract: A method, system and computer readable medium for performing a cognitive search operation comprising: receiving training data, the training data comprising information based upon user interaction with cognitive attributes; performing a machine learning operation on the training data; generating a cognitive profile based upon the information generated by performing the machine learning operation; and, performing a cognitive search operation on a corpus of content based upon the cognitive profile, the cognitive search operation returning cognitive results specific to the cognitive profile of the user.

Abstract: Disclosed herein is a method for using a neural network across multiple devices. The method can include receiving, by a first device configured with a first one or more layers of a neural network, input data for processing via the neural network implemented across the first device and a second device. The method can include outputting, by the first one or more layers of the neural network implemented on the first device, a data set that is reduced in size relative to the input data while identifying one or more features of the input data for processing by a second one or more layers of the neural network. The method can include communicating, by the first device, the data set to the second device for processing via the second one or more layers of the neural network implemented on the second device.

Abstract: Techniques for detecting state changes in a system may include receiving a first neural network that is trained to detect when the system transitions into a first resulting state, wherein the system transitions into at least a first intermediate state prior to transitioning into the final resulting state; training the first neural network using a first plurality of inputs denoting the system in the first intermediate state; obtaining a plurality of sets of internal state information of the first neural network, each set of the plurality of sets denoting an internal state of the first neural network at a different point in time after the first neural network has processed at least a portion of the first plurality of inputs; and training a second neural network, using the plurality of sets of internal state information, to detect the first intermediate state.

Abstract: Methods, systems, and computer-readable storage media for determining, by an automated regression detection system (ARDS), that training of a ML model is complete, the ML model being a version of a previously trained ML model, and in response, automatically, by the ARDS: retrieving the ML model, executing regression testing and detection using the ML model, generating regression results relative to the previously trained ML model, and publishing the regression results.

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.

Abstract: Digital content interaction prediction and training techniques that address imbalanced classes are described. In one or more implementations, a digital medium environment is described to predict user interaction with digital content that addresses an imbalance of numbers included in first and second classes in training data used to train a model using machine learning. The training data is received that describes the first class and the second class. A model is trained using machine learning. The training includes sampling the training data to include at least one subset of the training data from the first class and at least one subset of the training data from the second class. Iterative selections are made of a batch from the sampled training data. The iteratively selected batches are iteratively processed by a classifier implemented using machine learning to train the model.