The project aims to investigate how inherent geometrical properties of the data can be incorporated in deep learning methods. To be concrete, consider a supervised learning task. The data set having an ‘inherent geometrical property’ can mathematically expressed as the labels depending either invariantly or equivariantly on the data point with respect to some group action. Can this invariance/equivariance be guaranteed by a certain architecture design? Convolutional neural networks are in fact an example of such an architecture – if the input image is translated, the output of a convolutional layer is translated with it.
Page manager Published: Tue 15 Dec 2020.
Please fill in a message
Send message
Thanks! We have received your message. If you have left your email address, you will receive a response from the editor-in-chief within 2-3 working days.