主講人:王立聯(lián) 新加坡南洋理工大學(xué)教授
時(shí)間:2025年4月11日13:30
地點(diǎn):三號(hào)樓332報(bào)告廳
舉辦單位:數(shù)理學(xué)院
主講人介紹:王立聯(lián),新加坡南洋理工大學(xué)教授,長(zhǎng)期從事譜和高階數(shù)值方法及其應(yīng)用研究。他在《SIAM Journal on Numerical Analysis》、《SIAM Journal on Scientific Computing》、《SIAM Journal on Applied Mathematics》、《Mathematics of Computation》以及《Applied and Computational Harmonic Analysis》等國(guó)際計(jì)算應(yīng)用數(shù)學(xué)頂級(jí)學(xué)術(shù)期刊上發(fā)表學(xué)術(shù)論文100余篇,并由Springer-Verlag出版社出版學(xué)術(shù)專(zhuān)著1部《Spectral Methods, 2011》(合著),該專(zhuān)著當(dāng)前被引用2000多次。在國(guó)際重要學(xué)術(shù)會(huì)議作邀請(qǐng)報(bào)告60余次,包括2016年, 在第十一屆國(guó)際譜和高階方法國(guó)際會(huì)議(巴西)作一小時(shí)特邀報(bào)告,2019年在中國(guó)舉辦的第12屆中國(guó)計(jì)算數(shù)學(xué)年會(huì)上做大會(huì)報(bào)告。
內(nèi)容介紹:The Kolmogrov’s superposition theorem (KST, 1957) provides a way to represent a high-dimensional continuous function as a superposition of one-dimensional continuous functions. This mathematically elegant theorem has stimulated much research interest in constructing neural networks very recently. In this talk, we shall review some variants of KSTs and its constructive proofs, and discuss its potential in neural network applications.