Friday, 10 June 2022, 13:00 at This talk will be held in a hybrid format at MR 2, Centre of Mathematical Sciences, CB3 0WA. Alternatively you can also join with Zoom (see abstract for Zoom link). – This talk is on the analysis and applications of a constructive architecture for training Deep Neural Networks (DNNs), which are usually trained by End-to-End (E2E) gradient propagation with fixed depths. E2E training of DNNs has proven to offer impressive performances in a number of applications such as computer vision, machine …