首页|Data from Miami University Broaden Understanding of Machine Learning (Experiment al evaluation of a machine learning approach to improve the reproducibility of n etwork simulations)
Data from Miami University Broaden Understanding of Machine Learning (Experiment al evaluation of a machine learning approach to improve the reproducibility of n etwork simulations)
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-Researchers detail new data in artific ial intelligence.According to news reporting from Miami University by NewsRx jo urnalists,research stated,"A stochastic network simulation is verified when it s distribution of outputs is aligned with the ground truth,while tolerating dev iations due to variability in real-world measurements and the randomness of a st ochastic simulation." Our news reporters obtained a quote from the research from Miami University:"Ho wever,comparing distributions may yield false positives,as erroneous simulatio ns may have the expected distribution yet present aberrations in low-level patte rns.For instance,the number of sick individuals may present the right trend ov er time,but the wrong individuals were infected.We previously proposed an appr oach that transforms simulation traces into images verified by machine learning algorithms that account for low-level patterns.We demonstrated the viability of this approach when many simulation traces are compared with a large ground trut h data set.However,ground truth data are often limited.For example,a publica tion may include few images of their simulation as illustrations; hence,teams t hat independently re-implement the model can only compare low-level patterns with few cases."
NETL
NSTL
