Opening the Black Box: Low-Dimensional Dynamics in High-Dimensional Recurrent Neural Networks

DOI10.1162/NECO_a_00409zbMath1269.92007DBLPjournals/neco/SussilloB13OpenAlexW1980324747WikidataQ46165554 ScholiaQ46165554MaRDI QIDQ5327184

Omri Barak, David Sussillo

Publication date: 7 August 2013

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

Full work available at URL: https://doi.org/10.1162/neco_a_00409

Mathematics Subject Classification ID

Applications of mathematical programming (90C90) Neural networks for/in biological studies, artificial life and related topics (92B20) Computational methods for problems pertaining to biology (92-08)

Related Items (18)

Stimulus-Driven and Spontaneous Dynamics in Excitatory-Inhibitory Recurrent Neural Networks for Sequence Representation ⋮ A neural kernel method for capturing multiscale high-dimensional micromorphic plasticity of materials with internal structures ⋮ Exploring weight initialization, diversity of solutions, and degradation in recurrent neural networks trained for temporal and decision-making tasks ⋮ Mathematical imaging and surface processing. Abstracts from the workshop held August 21--27, 2022 ⋮ STDP-based associative memory formation and retrieval ⋮ Heterogeneity in Neuronal Dynamics Is Learned by Gradient Descent for Temporal Processing Tasks ⋮ Dynamics of spiking map-based neural networks in problems of supervised learning ⋮ Inference of a Mesoscopic Population Model from Population Spike Trains ⋮ A Robust Model of Gated Working Memory ⋮ Rat Prefrontal Cortex Inactivations during Decision Making Are Explained by Bistable Attractor Dynamics ⋮ A normative approach to neuromotor control ⋮ A Geometrical Analysis of Global Stability in Trained Feedback Networks ⋮ DNA Reservoir Computing: A Novel Molecular Computing Approach ⋮ One Step Back, Two Steps Forward: Interference and Learning in Recurrent Neural Networks ⋮ Collective dynamics of rate neurons for supervised learning in a reservoir computing system ⋮ Mapping Low-Dimensional Dynamics to High-Dimensional Neural Activity: A Derivation of the Ring Model From the Neural Engineering Framework ⋮ The Remarkable Robustness of Surrogate Gradient Learning for Instilling Complex Function in Spiking Neural Networks ⋮ Low-Dimensional Manifolds Support Multiplexed Integrations in Recurrent Neural Networks

Cites Work

• Unnamed Item
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• Chaos in Dynamical Systems
• Neural networks and physical systems with emergent collective computational abilities.

This page was built for publication: Opening the Black Box: Low-Dimensional Dynamics in High-Dimensional Recurrent Neural Networks