arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2201.09928cs.LOcs.LG
收藏

Learning Model Checking and the Kernel Trick for Signal Temporal Logic on Stochastic Processes

University of Trieste(的里雅斯特大学);Saarland University(萨尔兰大学);Technical University of Munich(慕尼黑工业大学);University of Technology, Vienna(维也纳技术大学)

Luca Bortolussi, Giuseppe Maria Gallo, Jan Křetínský, Laura Nenzi

英文摘要:

We introduce a similarity function on formulae of signal temporal logic (STL). It comes in the form of a kernel function, well known in machine learning as a conceptually and computationally efficient tool. The corresponding kernel trick allows us to circumvent the complicated process of feature extraction, i.e. the (typically manual) effort to identify the decisive properties of formulae so that learning can be applied. We demonstrate this consequence and its advantages on the task of predicting (quantitative) satisfaction of STL formulae on stochastic processes: Using our kernel and the kernel trick, we learn (i) computationally efficiently (ii) a practically precise predictor of satisfaction, (iii) avoiding the difficult task of finding a way to explicitly turn formulae into vectors of numbers in a sensible way. We back the high precision we have achieved in the experiments by a theoretically sound PAC guarantee, ensuring our procedure efficiently delivers a close-to-optimal predictor.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑