首页|Study Data from University of Kerala Provide New Insights into Human-Centric Int elligent Systems (A Local Explainability Technique for Graph Neural Topic Models )
Study Data from University of Kerala Provide New Insights into Human-Centric Int elligent Systems (A Local Explainability Technique for Graph Neural Topic Models )
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 Daily News – A new study on human-centric intellige nt systems is now available. According to news reporting from the University of Kerala by NewsRx journalists, research stated, “Topic modelling is a Natural Lan guage Processing (NLP) technique that has gained popularity in the recent past. It identifies word co-occurrence patterns inside a document corpus to reveal hid den topics.” The news correspondents obtained a quote from the research from University of Ke rala: “Graph Neural Topic Model (GNTM) is a topic modelling technique that uses Graph Neural Networks (GNNs) to learn document representations effectively. It p rovides high-precision documents-topics and topics-words probability distributio ns. Such models find immense application in many sectors, including healthcare, financial services, and safety-critical systems like autonomous cars. This model is not explainable. As a matter of fact, the user cannot comprehend the underly ing decision-making process. The paper introduces a technique to explain the doc uments-topics probability distributions output of GNTM. The explanation is achie ved by building a local explainable model such as a probabilistic Naive Bayes cl assifier.”
University of KeralaHuman-Centric Inte lligent SystemsMachine Learning
NETL
NSTL
