A gradient rule for the plasticity of a neuron’s intrinsic excitability

Authors:
Jochen Triesch
Affiliations:
Department of Cognitive Science, UC San Diego, La Jolla, CA
Venue:
ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
Year:
2005

Citing 1
Cited 14

An information-maximization approach to blind separation and blind deconvolution

Neural Computation

Learning sensory representations with intrinsic plasticity

Neurocomputing
Synergies Between Intrinsic and Synaptic Plasticity Mechanisms

Neural Computation
2007 Special Issue: Fading memory and time series prediction in recurrent networks with different forms of plasticity

Neural Networks
2007 Special Issue: Online reservoir adaptation by intrinsic plasticity for backpropagation-decorrelation and echo state learning

Neural Networks
Delay learning and polychronization for reservoir computing

Neurocomputing
Improving reservoirs using intrinsic plasticity

Neurocomputing
A Globally Asymptotically Stable Plasticity Rule for Firing Rate Homeostasis

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Learning inverse kinematics for pose-constraint bi-manual movements

SAB'10 Proceedings of the 11th international conference on Simulation of adaptive behavior: from animals to animats
Improving recurrent neural network performance using transfer entropy

ICONIP'10 Proceedings of the 17th international conference on Neural information processing: models and applications - Volume Part II
Intrinsic adaptation in autonomous recurrent neural networks

Neural Computation
Optimizing extreme learning machines via ridge regression and batch intrinsic plasticity

Neurocomputing
A self-organized neural comparator

Neural Computation
Intrinsic plasticity via natural gradient descent with application to drift compensation

Neurocomputing
Kinesthetic teaching of visuomotor coordination for pointing by the humanoid robot iCub

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

While synaptic learning mechanisms have always been a core topic of neural computation research, there has been relatively little work on intrinsic learning processes, which change a neuron’s excitability. Here, we study a single, continuous activation model neuron and derive a gradient rule for the intrinsic plasticity based on information theory that allows the neuron to bring its firing rate distribution into an approximately exponential regime, as observed in visual cortical neurons. In simulations, we show that the rule works efficiently.