Low-dimensional manifolds support multiplexed integrations in recurrent neural networks

DOI10.1162/NECO_A_01366OpenAlexW3124037805MaRDI QIDQ5004342FDOQ5004342

Authors: Arnaud Fanthomme, R. Monasson 

Publication date: 30 July 2021

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2011.10435

Recommendations

• Opening the black box: low-dimensional dynamics in high-dimensional recurrent neural networks
• Distributed sequence memory of multidimensional inputs in recurrent networks
• Shaping dynamics with multiple populations in low-rank recurrent networks
• Stimulus-Driven and Spontaneous Dynamics in Excitatory-Inhibitory Recurrent Neural Networks for Sequence Representation
• Elements for a general memory structure: properties of recurrent neural networks used to form situation models

Mathematics Subject Classification ID

Artificial intelligence (68Txx)

Cites Work

• Opening the black box: low-dimensional dynamics in high-dimensional recurrent neural networks

Cited In (3)

• Probing the relationship between latent linear dynamical systems and low-rank recurrent neural network models
• Opening the black box: low-dimensional dynamics in high-dimensional recurrent neural networks
• Shaping dynamics with multiple populations in low-rank recurrent networks

Uses Software

• SciPy
• PyTorch
• Adam
• DeepLoc

This page was built for publication: Low-dimensional manifolds support multiplexed integrations in recurrent neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5004342)