首页|Patent Issued for Explainable and automated decisions in computerbased reasonin g systems (USPTO 12067467)
Patent Issued for Explainable and automated decisions in computerbased reasonin g systems (USPTO 12067467)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – A patent by the inventors Fusting, Christopher (R aleigh, NC, US), Hazard, Christopher James (Raleigh, NC, US), Resnick, Michael ( Raleigh, NC, US), filed on July 5, 2023, was published online on August 20, 2024 , according to news reporting originating from Alexandria, Virginia, by NewsRx c orrespondents. Patent number 12067467 is assigned to Howso Incorporated (Raleigh, North Carolin a, United States). The following quote was obtained by the news editors from the background informa tion supplied by the inventors: “Machine learning systems can be used to predict outcomes based on input data. For example, given a set of input data, a regress ion-based machine learning system can predict an outcome. The regression-based m achine learning system will likely have been trained on much training data in or der to generate its regression model. It will then predict the outcome based on the regression model. “One issue with current systems is, however, that those predicted outcomes appea r without any indication of why a particular outcome has been predicted. For exa mple, a regression-based machine learning system will simply output a predicted result, and provide no indication of why that outcome was predicted. When machin e learning systems are used as decision-making systems, this lack of visibility into why the machine learning system has made its decisions can be an issue. For example, when the machine learning system makes a prediction, which is then use d as part of a decision, that decision is made without knowing why the machine l earning system predicted that particular outcome based on the input. When the pr ediction or subsequent decision is wrong, there is no way to trace back and asse ss why the prediction was made by the machine learning system.
BusinessCybersecurityCyborgsEmergi ng TechnologiesHowso IncorporatedInvestment and FinanceLegal IssuesMachi ne LearningSelf-Driving CarsTransportation
NETL
NSTL
