Journal article

ManifoldNet: A Deep Neural Network for Manifold-valued Data with Applications

Rudrasis Chakraborty, Jose Bouza, Jonathan Manton, Baba C Vemuri

IEEE Transactions on Pattern Analysis and Machine Intelligence | Institute of Electrical and Electronics Engineers (IEEE) | Published : 2020


Geometric deep learning is a relatively nascent field that has attracted significant attention in the recent past. This is partly due to the ready availability of manifold-valued data. In this paper we present a novel theoretical framework for developing deep neural networks to cope with manifold-valued fields as inputs. We also present a novel architecture to realize this theory and call it a ManifoldNet. Analogous to convolutions in vector spaces which are equivalent to computing weighted sums, manifold-valued data ‘convolutions’ can be defined using the weighted Frechet Mean (wFM), an intrinsic operation. The hidden layers of ManifoldNet compute wFM of their inputs, where the weights are ..

View full abstract