首页|University of Vienna Reports Findings in Machine Learning (Deciphering Molecular Embeddings with Centered Kernel Alignment)
University of Vienna Reports Findings in Machine Learning (Deciphering Molecular Embeddings with Centered Kernel Alignment)
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
New research on Machine Learning is th e subject of a report. According to news reporting originating from Vienna, Aust ria, by NewsRx correspondents, research stated, "Analyzing machine learning mode ls, especially nonlinear ones, poses significant challenges. In this context, ce ntered kernel alignment (CKA) has emerged as a promising model analysis tool tha t assesses the similarity between two embeddings." Our news editors obtained a quote from the research from the University of Vienn a, "CKA's efficacy depends on selecting a kernel that adequately captures the un derlying properties of the compared models. The model analysis tool was designed for neural networks (NNs) with their invariance to data rotation in mind and ha s been successfully employed in various scientific domains. However, CKA has rar ely been adopted in cheminformatics, partly because of the popularity of the ran dom forest (RF) machine learning algorithm, which is not rotationally invariant. In this work, we present the adaptation of CKA that builds on the RF kernel to match the properties of RF. As part of the method validation, we show that the m odel analysis method is well-correlated with the prediction similarity of RF mod els."
ViennaAustriaEuropeCyborgsEmergi ng TechnologiesMachine Learning
NETL
NSTL
