信息科學(xué)技術(shù)學(xué)院計(jì)算機(jī)科學(xué)系學(xué)術(shù)講座(二)
題目：PrincipledDesignofConvolutionalNeuralNetworks
內(nèi)容簡(jiǎn)介：The design of convolutional neural networks (CNNs) has undergone two phases: manual design at the early stage, which requires much engineering insights, and the automatic search at the current stage, which heavily relies on computing power. Whether there is an underlying theory for designing good CNNs becomes a crucial research problem. In this talk, I will illustrate our efforts on pursuing this goal. Although I haven’t found a unified principle that can result in all the effective CNNs, I do find multiple principles that can help design CNNs from various aspects.
報(bào)告人：北京大學(xué)林宙辰教授
報(bào)告人簡(jiǎn)介：博士生導(dǎo)師，IAPR/IEEE Fellow，國(guó)家杰青，中國(guó)圖象圖形學(xué)學(xué)會(huì)機(jī)器視覺(jué)專(zhuān)委會(huì)主任，中國(guó)自動(dòng)化學(xué)會(huì)模式識(shí)別與機(jī)器智能專(zhuān)委會(huì)副主任。研究領(lǐng)域?yàn)闄C(jī)器學(xué)習(xí)、計(jì)算機(jī)視覺(jué)和數(shù)值優(yōu)化。發(fā)表論文200余篇，英文專(zhuān)著2本。多次擔(dān)任CVPR 、ICCV、NIPS/NeurIPS、ICML、IJCAI、AAAI和ICLR領(lǐng)域主席，曾任IEEE T. PAMI編委，現(xiàn)任IJCV編委。
時(shí)間：2020年11月29日（周日）上午9：30開(kāi)始
地點(diǎn)：南海樓338室
熱烈歡迎廣大師生參加!
信息科學(xué)技術(shù)學(xué)院