Scattering Networks on Noncommutative Finite Groups

Scattering Networks were initially designed to elucidate the behavior of early layers in Convolutional Neural Networks (CNNs) over Euclidean spaces and are grounded in wavelets. In this work, we introduce a scattering transform on an arbitrary finite group (not necessarily abelian) within the context of group-equivariant convolutional neural networks (G-CNNs). We present wavelets on finite groups and analyze their similarity to classical wavelets. We demonstrate that, under certain conditions in the wavelet coefficients, the scattering transform is non-expansive, stable under deformations, preserves energy, equivariant with respect to left and right group translations, and, as depth increases, the scattering coefficients are less sensitive to group translations of the signal, all desirable properties of convolutional neural networks. Furthermore, we provide examples illustrating the application of the scattering transform to classify data with domains involving abelian and nonabelian groups.

GeometricImageNet: Extending convolutional neural networks to vector and tensor images

Convolutional neural networks and their ilk have been very successful for many learning tasks involving images. These methods assume that the input is a scalar image representing the intensity in each pixel, possibly in multiple channels for color images. In natural-science domains however, image-like data sets might have vectors (velocity, say), tensors (polarization, say), pseudovectors (magnetic field, say), or other geometric objects in each pixel. Treating the components of these objects as independent channels in a CNN neglects their structure entirely. Our formulation -- the GeometricImageNet -- combines a geometric generalization of convolution with outer products, tensor index contractions, and tensor index permutations to construct geometric-image functions of geometric images that use and benefit from the tensor structure. The framework permits, with a very simple adjustment, restriction to function spaces that are exactly equivariant to translations, discrete rotations, and reflections. We use representation theory to quantify the dimension of the space of equivariant polynomial functions on 2-dimensional vector images. We give partial results on the expressivity of GeometricImageNet on small images. In numerical experiments, we find that GeometricImageNet has good generalization for a small simulated physics system, even when trained with a small training set. We expect this tool will be valuable for scientific and engineering machine learning, for example in cosmology or ocean dynamics.