Lyapunov spectra of chaotic recurrent neural networks

R Engelken, F Wolf, LF Abbott - Physical Review Research, 2023 - APS
This article is part of the Physical Review Research collection titled Physics of
Neuroscience. Recurrent networks are widely used as models of biological neural circuits …

Sparseprop: Efficient event-based simulation and training of sparse recurrent spiking neural networks

R Engelken - Advances in Neural Information Processing …, 2023 - proceedings.neurips.cc
Abstract Spiking Neural Networks (SNNs) are biologically-inspired models that are capable
of processing information in streams of action potentials. However, simulating and training …

On lyapunov exponents for rnns: Understanding information propagation using dynamical systems tools

R Vogt, M Puelma Touzel, E Shlizerman… - Frontiers in Applied …, 2022 - frontiersin.org
Recurrent neural networks (RNNs) have been successfully applied to a variety of problems
involving sequential data, but their optimization is sensitive to parameter initialization …

[PDF][PDF] Chaotic neural circuit dynamics

R Engelken - 2017 - d-nb.info
Chaotic Neural Circuit Dynamics Page 1 Chaotic Neural Circuit Dynamics Dissertation for the
award of the degree “Doctor rerum naturalium” Division of Mathematics and Natural Sciences of …

Statistical mechanics of phase-space partitioning in large-scale spiking neuron circuits

MP Touzel, F Wolf - arxiv preprint arxiv:1703.05205, 2017 - arxiv.org
Synaptic interactions structure the phase space of the dynamics of neural circuits and
constrain neural computation. Understanding how requires methods that handle those …