Dynamics of neural networks with elapsed time model and learning processes
From MaRDI portal
(Redirected from Publication:829619)
Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Asymptotic behavior of solutions to PDEs (35B40) Nonlinear first-order PDEs (35F20) PDEs in connection with biology, chemistry and other natural sciences (35Q92) Integro-partial differential equations (35R09)
Abstract: We introduce and study a new model of interacting neural networks, incorporating the spatial dimension (e.g. position of neurons across the cortex) and some learning processes. The dynamic of each neural network is described via the elapsed time model, that is, the neurons are described by the elapsed time since their last discharge and the chosen learning processes are essentially inspired from the Hebbian rule. We then obtain a system of integro-differential equations, from which we analyze the convergence to stationary states by the means of entropy method and Doeblin's theory in the case of weak interconnections. We also consider the situation where neural activity is faster than the learning process and give conditions where one can approximate the dynamics by a solution with a similar profile of a steady state. For stronger interconnections, we present some numerical simulations to observe how the parameters of the system can give different behaviors and pattern formations.
Recommendations
- An elapsed time model for strongly coupled inhibitory and excitatory neural networks
- Weak and strong connectivity regimes for a general time elapsed neuron network model
- A multiple time renewal equation for neural assemblies with elapsed time model
- Relaxation and self-sustained oscillations in the time elapsed neuron network model
- Continuous neural network with windowed Hebbian learning
Cites work
- Adaptation and fatigue model for neuron networks and large time asymptotics in a nonlinear fragmentation equation
- Analysis of nonlinear noisy integrate \& fire neuron models: blow-up and steady states
- Asymptotic behaviour of neuron population models structured by elapsed-time
- Distributed synaptic weights in a LIF neural network and learning rules
- Dynamics of a structured neuron population
- Dynamics of pattern formation in lateral-inhibition type neural fields
- Dynamics of time elapsed inhomogeneous neuron network model
- Existence and stability of traveling pulses in a neural field equation with synaptic depression
- General relative entropy inequality: an illustration on growth models
- Localized states in an unbounded neural field equation with smooth firing rate function: a multi-parameter analysis
- Mean-field limit of a spatially-extended Fitzhugh-Nagumo neural network
- Microscopic approach of a time elapsed neural model
- Neural fields with fast learning dynamic kernel
- Qualitative properties of solutions for the noisy integrate and fire model in computational neuroscience
- Relaxation and self-sustained oscillations in the time elapsed neuron network model
- Relaxation in time elapsed neuron network models in the weak connectivity regime
- Rigorous derivation of the nonlocal reaction-diffusion FitzHugh-Nagumo system
- Some theoretical and numerical results for delayed neural field equations
- Spike Train Statistics and Dynamics with Synaptic Input from any Renewal Process: A Population Density Approach
- Spiking Neuron Models
Cited in
(8)- An elapsed time model for strongly coupled inhibitory and excitatory neural networks
- Microscopic approach of a time elapsed neural model
- Dynamics of time elapsed inhomogeneous neuron network model
- Multiscale analysis of slow-fast neuronal learning models with noise
- Concentration Phenomena in Fitzhugh–Nagumo Equations: A Mesoscopic Approach
- Exponential quasi-ergodicity for processes with discontinuous trajectories
- One dimensional reduction of a renewal equation for a measure-valued function of time describing population dynamics
- Pattern formation in a spiking neural-field of renewal neurons
This page was built for publication: Dynamics of neural networks with elapsed time model and learning processes
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q829619)
