Deep Function Machines


About This Project

Deep function machines (DFMs) are a generalization of deep neural networks proposed to connect topology in data to topology in neural networks. DFMs act on vector spaces of arbitrary (possibly infinite) dimension and in fact certain DFMs are invariant to the dimension of input data; that is, the parameterization of the model does not directly hinge on the quality of the input (eg. high resolution images). DFMs provide an expressive framework for designing new neural network layer types with topological considerations in mind.

Project Members

Deep Function Machines

currently no documents uploaded for this project

<< Back to Portfolio