You are all cordially invited to the AMLab seminar on Thursday November 29 at 16:00 in C3.163, where Daniel Worrall will give a talk titled “Semigroup Convolutional Neural Networks: Merging Scale-space and Deep Learning”. Afterwards there are the usual drinks and snacks!
Abstract: Group convolutional neural networks (GCNN) are symmetric under predefined, invertible transformations in the input e.g. rotations, flips, and translations. Can we extend this framework in the absence of invertibility, for instance in the case of pixelated image downscalings, or causal time-shifting of audio signals? To this end, I present Semigroup Convolutional Neural Networks (SCNN), a generalisation of GCNNs based on the related theory of semigroups. I will showcase a specialisation of a scale-equivariant SCNN, where the activations of each layer of the network live on a classical scale-space, finally linking the classical field of scale-spaces and modern deep learning.