Spiking Neurons Can Learn to Solve Information Bottleneck Problems and Extract Independent Components

DOI10.1162/NECO.2008.01-07-432zbMath1157.92302OpenAlexW2080693060WikidataQ48822074 ScholiaQ48822074MaRDI QIDQ3616496

Robert A. Legenstein, Stefan Klampfl, Wolfgang Maass

Publication date: 25 March 2009

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

Full work available at URL: https://doi.org/10.1162/neco.2008.01-07-432

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural biology (92C20)

Related Items (4)

Reservoir computing approaches to recurrent neural network training ⋮ A Reward-Maximizing Spiking Neuron as a Bounded Rational Decision Maker ⋮ A Spiking Neuron as Information Bottleneck ⋮ Function identification in neuron populations via information bottleneck

Cites Work

• Unnamed Item
• Independent component analysis by general nonlinear Hebbian-like learning rules
• Spiking Neuron Models
• What Can a Neuron Learn with Spike-Timing-Dependent Plasticity?

This page was built for publication: Spiking Neurons Can Learn to Solve Information Bottleneck Problems and Extract Independent Components