首页|Findings on Machine Learning Discussed by Investigators at Wuhan University (Int erpretable Machine Learning of Spac System Via a Mechanism-assisted Gaussian Pro cess Group: Representation of the System Mechanism By Data)
Findings on Machine Learning Discussed by Investigators at Wuhan University (Int erpretable Machine Learning of Spac System Via a Mechanism-assisted Gaussian Pro cess Group: Representation of the System Mechanism By Data)
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-Fresh data on Machine Learning are pre sented in a new report. According to news reporting originating from Hubei, Peop le's Republic of China, by NewsRx correspondents, research stated, "Traditional models of the soil -plant -atmosphere continuum (SPAC) system are physics -based and their practical application has been hindered by issues of high parameteriz ation, prior structural bias, and costly running. In this paper, we developed a machine learning modelling method based on the Gaussian process (GP) to avoid th ese difficulties of traditional modelling." Funders for this research include Priority Research and Development Projects for Ningxia, National Natural Science Foundation of China (NSFC). Our news editors obtained a quote from the research from Wuhan University, "At t he same time, shortcomings of conventional machine learning in terms of interpre tability and mechanism representation were addressed. The innovative method cons isted of structuring a local GP group framework and improving kernel functions u sed in each local GP. The resultant model was endowed with advanced capacities, including representing interplays between subprocesses within the complex SPAC s ystem, representing nonstationary subprocess dynamics caused by crop growth stag e shifts, as well as automatically interpreting key low -order input interaction s and dominant input variables for each subprocess. The performance of our model was examined on synthetic SPAC system datasets that covered three different soi l conditions. Results demonstrated that its interpretations regarding subprocess mechanisms were robust across different soil conditions and consistent with dom ain knowledge. Compared to a conventional global GP model and two deep learning models (DNN and LSTM), our model performed significantly better not only in regu lar prediction experiments but also in generalization experiments that required models to be transferred across different conditions. Our study suggested that i t is promising to enable a machine learning model interpretable by improving its feature representation function."
HubeiPeople's Republic of ChinaAsiaCyborgsEmerging TechnologiesGaussian ProcessesMachine LearningWuhan Uni versity
NETL
NSTL
