A topological model for partial equivariance in deep learning and data analysis
In this article, we propose a topological model to encode partial equivariance in neural networks. To this end, we introduce a class of operators, called P-GENEOs, that change data expressed by measurements, respecting the action of certain sets of transformations, in a non-expansive way. If the set of transformations acting is a group, then we obtain the so-called GENEOs. We then study the spaces of measurements, whose domains are subject to the action of certain self-maps, and the space of P-GENEOs between these spaces. We define pseudo-metrics on them and show some properties of the resulting spaces. In particular, we show how such spaces have convenient approximation and convexity properties.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Learning Partial Equivariances from Data
Group Convolutional Neural Networks (G-CNNs) constrain learned features to respect the symmetries in the selected group, and lead to better generalization when these symmetries appear in the data. If this is not the case…
Image ClassificationRotated MNISTVariational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-Shifts
Group Equivariant CNNs (G-CNNs) have shown promising efficacy in various tasks, owing to their ability to capture hierarchical features in an equivariant manner. However, their equivariance is fixed to the symmetry of th…
Variational InferenceA General Theory of Correct, Incorrect, and Extrinsic Equivariance
Although equivariant machine learning has proven effective at many tasks, success depends heavily on the assumption that the ground truth function is symmetric over the entire domain matching the symmetry in an equivaria…
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions
Recent research has shown that incorporating equivariance into neural network architectures is very helpful, and there have been some works investigating the equivariance of networks under group actions. However, as digi…
image-classificationImage ClassificationRotated MNISTLeveraging Equivariances and Symmetries in the Control Barrier Function Synthesis
The synthesis of Control Barrier Functions (CBFs) often involves demanding computations or a meticulous construction. However, structural properties of the system dynamics and constraints have the potential to mitigate t…