Stimulus-Driven and Spontaneous Dynamics in Excitatory-Inhibitory Recurrent Neural Networks for Sequence Representation

DOI10.1162/NECO_A_01418zbMATH Open1483.92019OpenAlexW3175513531MaRDI QIDQ5033544FDOQ5033544

Authors Alfred Rajakumar, John Rinzel, Zhe S. Chen

Publication date 23 February 2022

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/neco_a_01418

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• scientific article; zbMATH DE number 1928616
• Spiking neuron model for temporal sequence recognition
• Dynamics of a recurrent network of spiking neurons before and following learning
• Relating the sequential dynamics of excitatory neural networks to synaptic cellular automata
• Transient dynamics for sequence processing neural networks
• Excitable networks for finite state computation with continuous time recurrent neural networks
• Spontaneous Dynamics of Asymmetric Random Recurrent Spiking Neural Networks

Cites work

• A neural network for storing individual patterns in limit cycles
• Computing the Polar Decomposition—with Applications
• Dynamics of sparsely connected networks of excitatory and inhibitory spiking neurons.
• Encoding time in feedforward trajectories of a recurrent neural network model
• Multistability in Recurrent Neural Networks
• Opening the black box: low-dimensional dynamics in high-dimensional recurrent neural networks
• Overcoming catastrophic forgetting in neural networks
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• Synthesis of recurrent neural networks for dynamical system simulation
• The echo index and multistability in input-driven recurrent neural networks

Cited in

(9)

• One step back, two steps forward: interference and learning in recurrent neural networks
• Sequential dynamics in the motif of excitatory coupled elements
• Low-dimensional manifolds support multiplexed integrations in recurrent neural networks
• Training spiking neural networks in the strong coupling regime
• Generation of scale-invariant sequential activity in linear recurrent networks
• Encoding time in feedforward trajectories of a recurrent neural network model
• Learning to generate combinatorial action sequences utilizing the initial sensitivity of deterministic dynamical systems
• Exploring weight initialization, diversity of solutions, and degradation in recurrent neural networks trained for temporal and decision-making tasks
• Learning sequence attractors in recurrent networks with hidden neurons

This page was built for publication: Stimulus-Driven and Spontaneous Dynamics in Excitatory-Inhibitory Recurrent Neural Networks for Sequence Representation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5033544)