Sep 2026
Shaping Slow Manifolds in Equivariant Recurrent Neural Networks.
This work introduces a new class of equivariant recurrent neural networks, where the connectivity is based on group convolution, and reduces such networks to low-rank models using the group Fourier transform.
Arianna di Bernardo, Adrian Valente, Francesca Mastrogiuseppe et al.
· Neural Computation · 0 citations