講座主題:Machine learning for inverse scattering problems
專家姓名:張凱
工作單位:吉林大學(xué)
講座時(shí)間:2021年11月18日 14:30-18:00
講座地點(diǎn):https://meeting.tencent.com/dm/ACinixBYR5hp 會(huì)議ID:246 795 051
主辦單位:煙臺(tái)大學(xué)數(shù)學(xué)與信息科學(xué)學(xué)院
內(nèi)容摘要:
In this presentation, we consider artificial neural networks for inverse scattering problems. As a working model, we consider the inverse problem of recovering a scattering object from the (possibly) limited-aperture radar cross section (RCS) data collected corresponding to a single incident field. From a geometrical and physical point of view, the low-frequency data should be able to resolve the unique identifiability issue, but meanwhile lose the resolution. On the other hand, the machine learning can be used to break through the resolution limit. By combining the two perspectives, we develop a fully connected neural network (FCNN) for the inverse problem. Extensive numerical results show that the proposed method can produce stunning reconstructions.
主講人介紹:
張凱,,2006年獲吉林大學(xué)博士學(xué)位,2008年獲得香港中文大學(xué)聯(lián)合培養(yǎng)博士學(xué)位,。2008-2010年,,赴密歇根州立大學(xué)開展博士后工作,現(xiàn)為吉林大學(xué)唐敖慶特聘教授,。張凱教授先后赴伊利諾伊州立大學(xué),,奧本大學(xué),香港浸會(huì)大學(xué),,南方科技大學(xué)等開展合作研究,,研究興趣為隨機(jī)偏微分方程的數(shù)值解法。主要從事隨機(jī)麥克斯韋方程和隨機(jī)聲波方程數(shù)值方法,,期權(quán)定價(jià)和套利的數(shù)值方法研究,。先后主持國家自然科學(xué)基金等項(xiàng)目11項(xiàng),發(fā)表論文50余篇,。期刊審稿人,。