COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Isaac Newton Institute Seminar Series > PDE-based Algorithms for Convolution Neural Network
PDE-based Algorithms for Convolution Neural NetworkAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact INI IT. VMVW02 - Generative models, parameter learning and sparsity This talk presents a new framework for image classification that exploits the relationship between the training of deep Convolution Neural Networks (CNNs) to the problem of optimally controlling a system of nonlinear partial differential equations (PDEs). This new interpretation leads to a variational model for CNNs, which provides new theoretical insight into CNNs and new approaches for designing learning algorithms. We exemplify the myriad benefits of the continuous network in three ways. First, we show how to scale deep CNNs across image resolutions using multigrid methods. Second, we show how to scale the depth of deep CNNS in a shallow-to-deep manner to gradually increase the flexibility of the classifier. Third, we analyze the stability of CNNs and present stable variants that are also reversible (i.e., information can be propagated from input to output layer and vice versa), which in combination allows training arbitrarily deep networks with limited computational resources. This is joint work with Eldad Haber (UBC), Lili Meng (UBC), Bo Chang (UBC), Seong-Hwan Jun (UBC), Elliot Holtham (Xtract Technologies) This talk is part of the Isaac Newton Institute Seminar Series series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsThe Politics of Economics Political Thought and Intellectual History Computer Laboratory Programming Research Group SeminarOther talksAn intellectual history of the universal basic income Regulation of progenitor cells in adult lung and in lung cancer Lipschitz Global Optimization How to rediscover a medical secret in eighteenth-century France: the lost recipe of the Chevalier de Guiller's powder febrifuge Statistical analysis of biotherapeutic datasets to facilitate early ‘Critical Quality Attribute’ characterization. UK 7T travelling-head study: pilot results |