As recorded neural populations become larger and artificial networks more powerful, there is growing interest in understanding and comparing what different populations encode. Representational geometry offers a powerful way to characterise this: it remaps stimulus space to stretch well-encoded stimulus differences whil...
Simone Azeglio, Steeve Laquitaine, Arianna di Bernardo et al.· bioRxiv· 0 citations
Neural activity during performance of a cognitive or motor task is often described as lying on a low-dimensional manifold in the space of all possible activity patterns. When multiple tasks are performed, an individual brain region’s activity may generate multiple such manifolds. Several models have been introduced to...
Manuel Beirán, Owen Marschall, Klavdia Zemlianova et al.· bioRxiv· 0 citations
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
The equivariance relaxation morphism, which preserves functionality while reparameterizing a group equivariant layer to operate with equivariance constraints on a subgroup, and the [ G ]-mixed equivariant layer, which mixes operations constrained to equivariance to different groups to enable within-layer equivariance o...
Kaitlin Maile, Dennis G. Wilson, Patrick Forré et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.