Differential Geometry Methods for Constructing Manifold-Targeted Recurrent Neural Networks

DOI10.1162/NECO_A_01511MaRDI QIDQ5095901zbMATH OpenOpenAlexWikidataFDO

Authors Federico Claudi, Tiago Branco

Publication date 11 August 2022

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/neco_a_01511

Mathematics Subject Classification ID

Differential geometry (53-XX) Computer science (68-XX)

Recommendations

• Cognition: Differential-geometrical view on neural networks
• A Geometrical Analysis of Global Stability in Trained Feedback Networks
• Shaping dynamics with multiple populations in low-rank recurrent networks
• Understanding recurrent neural networks using nonequilibrium response theory

Cited in

(3)

• Deep learning Gauss-Manin connections
• STDP-based associative memory formation and retrieval
• Riemannian metrics for neural networks II: recurrent networks and learning symbolic data sequences

This page was built for publication: Differential Geometry Methods for Constructing Manifold-Targeted Recurrent Neural Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5095901)