A Gradient Learning Rule for the Tempotron

DOI10.1162/NECO.2008.09-07-605MaRDI QIDQ3612122zbMATH OpenOpenAlexWikidataFDO

Authors Walter Senn, R. Urbanczik

Publication date 3 March 2009

Published in Neural Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1162/neco.2008.09-07-605

zbMATH Keywords

supervised learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Recommendations

• A gradient descent rule for spiking neurons emitting multiple spikes
• Training the integrate-and-fire model with the informax principle: I
• Spike-Timing Error Backpropagation in Theta Neuron Networks
• A supervised multi-spike learning algorithm based on gradient descent for spiking neural networks
• A new supervised learning algorithm for spiking neurons

Cites work

• Modeling single-neuron dynamics and computations: a balance of detail and abstraction
• Optimal Spike-Timing-Dependent Plasticity for Precise Action Potential Firing in Supervised Learning
• Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity

Cited in

(4)

• A gradient descent rule for spiking neurons emitting multiple spikes
• Extending the mirror neuron system model. II: What did I just do? A new role for mirror neurons
• Training the integrate-and-fire model with the informax principle: I
• SuperSpike: supervised learning in multilayer spiking neural networks

This page was built for publication: A Gradient Learning Rule for the Tempotron

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3612122)