Search Results for author:
Found 7 papers, 2 papers with code
Brief technical note on linearizing recurrent neural networks (RNNs) before vs after the pointwise nonlinearity
Linearization of the dynamics of recurrent neural networks (RNNs) is often used to study their properties.
The computational role of structure in neural activity and connectivity
One major challenge of neuroscience is finding interesting structures in a seemingly disorganized neural activity.
Aligned and oblique dynamics in recurrent neural networks
Here, we utilize recurrent neural networks (RNNs) to explore the question of when and how neural dynamics and the network's output are related from a geometrical point of view.
Probing the relationship between linear dynamical systems and low-rank recurrent neural network models
We show that latent LDS models can only be converted to RNNs in specific limit cases, due to the non-Markovian property of latent LDS models.
Interpreting neural computations by examining intrinsic and embedding dimensionality of neural activity
The ongoing exponential rise in recording capacity calls for new approaches for analysing and interpreting neural data.
The interplay between randomness and structure during learning in RNNs
Recurrent neural networks (RNNs) trained on low-dimensional tasks have been widely used to model functional biological networks.
Disentangling the roles of dimensionality and cell classes in neural computations
In these networks, the rank of the connectivity controls the dimensionality of the dynamics, while the number of components in the Gaussian mixture corresponds to the number of cell classes.
