Hi.q, Inc.

Xilinx, Inc.

Shuo Jiao

Munjal Shah

Ardaman Singh

Ryan Hinchey

Cathy Ye Fan

Romi Mayder

Bowen Li

Geoffrey Zhang

Apparatus and associated methods relate to predicting various transient output waveforms at a receiver's output after an initial neural network model is trained by a receiver's transient input waveform and a corresponding transient output waveform. In an illustrative example, the machine learning model may include an adaptive-ordered auto-regressive moving average external input based on neural networks (NNARMAX) model designed to mimic the performance of a continuous time linear equalization (CTLE) mode of the receiver. A Pearson Correlation Coefficient (PCC) score may be determined to select numbers of previous inputs and previous outputs to be used in the neural network model. In other examples, corresponding bathtub characterizations and eye diagrams may be extracted from the predicted transient output waveforms. Providing a machine learning model may, for example, advantageously predict various data patterns without knowing features or parameters of the receiver or related channels.

Machine learning based methodology for signal waveform, eye diagram, and bit error rate (BER) bathtub prediction

A computing system can implement a health verification and prediction service by generating an interactive user interface through which users can provide responses to health assertions in one or more trivia sessions. Each of the health assertions can include a correlation value to actual health outcomes based on responses received from individuals a control group and the known health outcomes of those individuals. Based on the responses from the user, the computing system can generate a health profile for the user.

Remote health assertion verification and mortality prediction system

A computing system can execute a correlation model for a library of health assertions to configure a correlation value for each health assertion. The correlation value comprises a correlation between knowledge associated with the health assertion and known health outcomes of individuals in a control group who have also provided responses to the health assertions. The computing system provides a health trivia session for users and based at least in part on the performance of the user, generates a morbidity risk profile that is used to classify the user in an underwriting class.

Computing system implementing morbidity prediction using a correlative health assertion library

Apparatus and associated methods relate to providing a machine learning methodology that uses the machine learning's own failure experiences to optimize future solution search and provide self-guided information (e.g., the dependency and independency among various adaptation behavior) to predict a receiver's equalization adaptations. In an illustrative example, a method may include performing a first training on a first neural network model and determining whether all of the equalization parameters are tracked. If not all of the equalization parameters are tracked under the first training, then, a second training on a cascaded model may be performed. The cascaded model may include the first neural network model, and training data of the second training may include successful learning experiences and data of the first neural network model. The prediction accuracy of the trained model may be advantageously kept while having a low demand for training data.

Machine learning based methodology for adaptative equalization

A computing system includes a database having a collection of health-related assertions for a health quiz to be taken by users. Each health assertion is tuned with a correlative health value based on answers to the health assertion provided by a control group of users. For each user in the control group, at least one health outcome is known, and therefore the computing system can use a big data approach to determine the correlative value for each health assertion to the actual health outcomes of the control group users. Using the correlative values for each health assertion, the computing system can generate a health profile of each user who takes the health quiz. In certain examples, the health quiz correlation can be combined with activity monitoring data to develop a highly accurate health profile for each user.

Computing system implementing a health service for correlating health knowledge and activity data with predictive health outcomes

A computing system can execute a correlation model to determine correlation values for health assertions, where the correlation value for each health assertion indicates a level of correlation between the health assertion and one or more actual health outcomes. Actual health outcomes are provided by control group users who have also provided responses, either correct or incorrect, to each of the health assertions. The computing system may then provide users with a health trivia session comprised of these health assertions, and based at least in part on the performance of the user during the trivia session, generate a health profile for the user.

Computing system predicting health using correlated health assertion library

Remote health assertion verification and health prediction system

A computing system can execute a correlation model for a library of health assertions to configure a correlation value for each health assertion. The correlation value comprises a correlation between knowledge associated with the health assertion and known health outcomes of individuals in a control group who have also provided responses to the health assertions. The computing system provides a health trivia session for users and based at least in part on the performance of the user, generates a mortality outcome profile that is used to classify the user in an underwriting class.

Computing system implementing mortality prediction using a correlative health assertion library

A system and method for predicting a health outcome of a user based on a determination of knowledge the user possesses regarding issues of physiological or mental health.

System and method for making a human health prediction for a person through determination of health knowledge

Examples described herein include a computer system to obtain social network content from a user, and to analyze the social network content to determine one or more attributes. The computer system predicts a lifestyle category of the user based at least in part on the determined one or more attributes.

System and method for using social network content to determine a lifestyle category of users

A computer system automates the determination of a health profile of a user based on a knowledge of the user regarding health related questions and social network content from an account of the user.

Automated determination of user health profile

Examples are provided herein for providing a service in connection with determining a health of a user. A collection of questions are stored for the user, with each question being based on a documented assertion pertaining to human health. Each question in the collection of questions is associated with a correlative health parameter that is based at least in part on (i) persons in a control population that have independent knowledge of an assertion that is a basis of that question, and (ii) a value of a predetermined health parameter for each person in the control population, the value of the predetermined health parameter for each person being indicative of that person's health. Based on data generated by one or more activity monitoring devices, questions from the collection are selected for display to the user.

System and method for providing a health determination service based on user knowledge and activity

A computer system prompts a user to answer a series of questions from a collection of questions. From the user's answers, the computer system predicts a mortality outcome based on the value of a predetermined mortality parameter for one or more of the questions in the series.

System and method for predicting mortality amongst a user base

A network computing system implements a health service comprising a health trivia game and connects, over one or more wireless networks, with the computing devices of users of the health service. The network computing system provides sequences of topical health questions and receives corresponding sequences of responses from the users. Based on a correctness of each response, the network computing system determines a predicted health outcome of a respective user of the health service, and generates a health report that is accessible via a user interface of the health trivia game.

Growing community of inventors

Sunnyvale, CA, United States of America

Shuo Jiao