Optimal sequence memory in driven random networks
Autonomous, randomly coupled, neural networks display a transition to chaos at a critical
coupling strength. Here, we investigate the effect of a time-varying input on the onset of …
coupling strength. Here, we investigate the effect of a time-varying input on the onset of …
Forgetting leads to chaos in attractor networks
Attractor networks are an influential theory for memory storage in brain systems. This theory
has recently been challenged by the observation of strong temporal variability in neuronal …
has recently been challenged by the observation of strong temporal variability in neuronal …
Gradient flossing: Improving gradient descent through dynamic control of jacobians
R Engelken - Advances in Neural Information Processing …, 2024 - proceedings.neurips.cc
Training recurrent neural networks (RNNs) remains a challenge due to the instability of
gradients across long time horizons, which can lead to exploding and vanishing gradients …
gradients across long time horizons, which can lead to exploding and vanishing gradients …
Decomposing neural networks as mappings of correlation functions
Understanding the functional principles of information processing in deep neural networks
continues to be a challenge, in particular for networks with trained and thus nonrandom …
continues to be a challenge, in particular for networks with trained and thus nonrandom …
Unified field theoretical approach to deep and recurrent neuronal networks
K Segadlo, B Epping, A Van Meegen… - Journal of Statistical …, 2022 - iopscience.iop.org
Understanding capabilities and limitations of different network architectures is of
fundamental importance to machine learning. Bayesian inference on Gaussian processes …
fundamental importance to machine learning. Bayesian inference on Gaussian processes …
Thermodynamic formalism in neuronal dynamics and spike train statistics
The Thermodynamic Formalism provides a rigorous mathematical framework for studying
quantitative and qualitative aspects of dynamical systems. At its core, there is a variational …
quantitative and qualitative aspects of dynamical systems. At its core, there is a variational …
Theory of spike-train power spectra for multidimensional integrate-and-fire neurons
Multidimensional stochastic integrate-and-fire (IF) models are a standard spike-generator
model in studies of firing variability, neural information transmission, and neural network …
model in studies of firing variability, neural information transmission, and neural network …
Integration of continuous-time dynamics in a spiking neural network simulator
J Hahne, D Dahmen, J Schuecker… - Frontiers in …, 2017 - frontiersin.org
Contemporary modeling approaches to the dynamics of neural networks include two
important classes of models: biologically grounded spiking neuron models and functionally …
important classes of models: biologically grounded spiking neuron models and functionally …
Neural network representation of quantum systems
K Hashimoto, Y Hirono, J Maeda… - arXiv preprint arXiv …, 2024 - arxiv.org
It has been proposed that random wide neural networks near Gaussian process are
quantum field theories around Gaussian fixed points. In this paper, we provide a novel map …
quantum field theories around Gaussian fixed points. In this paper, we provide a novel map …