99 citations · 104 across the 4 of their papers we have counts for
4 papers
Shaping manifolds in equivariant recurrent neural networks
Arianna Di Bernardo, Adrian Valente, Francesca Mastrogiuseppe +1
Recordings of increasingly large neural populations have revealed that the firing of individual neurons is highly coordinated. When viewed in the space of all possible patterns, th…
Brief technical note on linearizing recurrent neural networks (RNNs) before vs after the pointwise nonlinearity
Marino Pagan, Adrian Valente, Srdjan Ostojic +1
Linearization of the dynamics of recurrent neural networks (RNNs) is often used to study their properties. The same RNN dynamics can be written in terms of the ``activations" (the…
Probing the relationship between linear dynamical systems and low-rank recurrent neural network models
Adrian Valente, Srdjan Ostojic, Jonathan Pillow
A large body of work has suggested that neural populations exhibit low-dimensional dynamics during behavior. However, there are a variety of different approaches for modeling low-d…
Shaping dynamics with multiple populations in low-rank recurrent networks
Manuel Beiran, Alexis Dubreuil, Adrian Valente +2
An emerging paradigm proposes that neural computations can be understood at the level of dynamical systems that govern low-dimensional trajectories of collective neural activity. H…