Fading memory and time series prediction in recurrent networks with different forms of plasticity

DOI10.1016/j.neunet.2007.04.020zbMath1132.68567WikidataQ51912990 ScholiaQ51912990MaRDI QIDQ2373494

Jochen Triesch, Andreea Lazar, Gordon Pipa

Publication date: 11 July 2007

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2007.04.020

zbMATH Keywords

time series; recurrent neural networks; intrinsic plasticity; spike timing dependent plasticity

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

Related Items

Connectivity, Dynamics, and Memory in Reservoir Computing with Binary and Analog Neurons

Cites Work

• Unnamed Item
• A computational framework for cortical learning
• Generalization in Interactive Networks: The Benefits of Inhibitory Competition and Hebbian Learning
• A Simple Neural Network Exhibiting Selective Activation of Neuronal Ensembles: From Winner-Take-All to Winners-Share-All
• Synergies Between Intrinsic and Synaptic Plasticity Mechanisms
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• Spike-Timing-Dependent Plasticity and Relevant Mutual Information Maximization
• Bayesian Computation in Recurrent Neural Circuits
• Real-Time Computation at the Edge of Chaos in Recurrent Neural Networks
• Neural networks and physical systems with emergent collective computational abilities.
• What Can a Neuron Learn with Spike-Timing-Dependent Plasticity?