Derives via two-site cavity method that nonlinear RNN covariance matrix equals that of linear equivalent network at large N for typical random couplings.
Optimal sequence memory in driven random networks.Physical Review X, 8(4):041029
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Simulation study finds embedding network in cortical microcolumn model enhances core information flux through biases and recurrence resonance.
citing papers explorer
-
Linear equivalence of nonlinear recurrent neural networks
Derives via two-site cavity method that nonlinear RNN covariance matrix equals that of linear equivalent network at large N for typical random couplings.
-
Are cortical microcircuits optimized for information flux? -- A simulation-based reverse engineering study
Simulation study finds embedding network in cortical microcolumn model enhances core information flux through biases and recurrence resonance.