題目:A Joint Matrix Minimization Approach for Pattern Recognition
報(bào)告人:王麗平 教授 (理學(xué)院)
時(shí)間:2019年12月5日14:00-15:00
地點(diǎn):將軍路校區(qū)理學(xué)院547室
承辦單位:南航青聯(lián)會(huì)、理學(xué)院、校科協(xié)
報(bào)告人簡(jiǎn)介:
王麗平,女,山東菏澤人。2004年畢業(yè)于中國科學(xué)院數(shù)學(xué)與系統(tǒng)科學(xué)研究院,獲博士學(xué)位,同年入職南航理學(xué)院工作至今。2009.2-2010.2在巴西巴拉納聯(lián)邦大學(xué)完成博士后項(xiàng)目,2013年11月和2017年8月兩次訪問俄羅斯科學(xué)院計(jì)算中心,2017年5-6月訪問香港中文大學(xué)系統(tǒng)工程與工程管理學(xué)系,2017.10-2018.10在美國路易斯安娜州立大學(xué)科學(xué)計(jì)算中心做公費(fèi)訪問學(xué)者。主要研究方向?yàn)樽顑?yōu)化理論與方法,數(shù)值優(yōu)化算法在模式識(shí)別、地球物理和醫(yī)學(xué)領(lǐng)域的應(yīng)用等。以第一/通訊作者發(fā)表論文三十余篇,其中SCI/EI檢索論文二十篇。自2012年起擔(dān)任中國運(yùn)籌學(xué)會(huì)理事,先后主持國家自然科學(xué)基金5項(xiàng),已完成4項(xiàng),在研1項(xiàng)。
報(bào)告摘要:
In this talk, a kind of pseudo matrix norm with is defined which is thought to be a joint generalization of vector norm and matrix norm . The joint matrix minimization model is often used in pattern recognition to take account of multiple features or samples simultaneously. When , the matrix minimization problem with -norm can find a joint and sparser solution than traditional measurements. To efficiently solve the related matrix minimization problem, a unified algorithm is proposed and its convergence is also demonstrated for a range of . Typical values of are employed for feature selection and collective image recognition. Extensive experiments on public data confirm the outperformance of joint matrix minimization approach over the state-of-the-arts.
Keywords: Joint matrix minimization; Feature selection; Collective image recognition; Numerical convergence