skip to main content

Mathematics & Machine Learning Seminar

Tuesday, February 13, 2024
2:00pm to 3:00pm
Add to Cal
East Bridge 114
Robust G-Invariance in G-Equivariant Networks
Nina Miolane, Department of Electrical & Computer Engineering, UC Santa Barbara,

Group-Equivariant Convolutional Neural Networks (G-CNNs) generalize the translation-equivariance of traditional CNNs to group-equivariance, using more general symmetry transformations such as rotations for weight tying. For tasks such as classification, such transformations are ultimately removed via pooling to achieve group-invariance and improve classification accuracy.

In this talk, we argue that traditional pooling operations are excessively invariant, resulting in a general lack of robustness to adversarial attacks both in classical CNNs and in G-CNNs. We propose alternative approaches to achieve robust invariance in CNNs and G-CNNs through two computational primitives: the G-triple correlation and its G-Fourier transform, the G-Bispectrum. This talk presents their mathematical properties with an introduction to group representation theory, and demonstrates gains in accuracy and robustness upon incorporating them in neural network architectures.

For more information, please contact Math Department by phone at 626-395-4335 or by email at [email protected].