Strongly Improved Stability and Faster Convergence of Temporal Sequence Learning by Using Input Correlations Only

DOI10.1162/neco.2006.18.6.1380zbMath1095.68651OpenAlexW2105780862WikidataQ51183866 ScholiaQ51183866MaRDI QIDQ5474567

Florentin Wörgötter, Bernd Porr

Publication date: 26 June 2006

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

Full work available at URL: https://doi.org/10.1162/neco.2006.18.6.1380

zbMATH Keywords

network learning algorithms

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (6)

Behavioral analysis of differential Hebbian learning in closed-loop systems ⋮ Model checking learning agent systems using Promela with embedded C code and abstraction ⋮ A differential Hebbian framework for biologically-plausible motor control ⋮ Mathematical properties of neuronal TD-rules and differential Hebbian learning: a comparison ⋮ Learning with “Relevance”: Using a Third Factor to Stabilize Hebbian Learning ⋮ Closed-Loop Deep Learning: Generating Forward Models With Backpropagation

Cites Work

• A simplified neuron model as a principal component analyzer
• Neural theory of association and concept-formation
• Computational consequences of temporally asymmetric learning rules. I: Differential Hebbian learning
• Temporal Difference Model Reproduces Anticipatory Neural Activity
• Isotropic Sequence Order Learning
• ISO Learning Approximates a Solution to the Inverse-Controller Problem in an Unsupervised Behavioral Paradigm

This page was built for publication: Strongly Improved Stability and Faster Convergence of Temporal Sequence Learning by Using Input Correlations Only