Incremental Slow Feature Analysis: Adaptive Low-Complexity Slow Feature Updating from High-Dimensional Input Streams

DOI10.1162/NECO_A_00344zbMath1268.68138OpenAlexW2038101149WikidataQ44376792 ScholiaQ44376792MaRDI QIDQ2840877

Jürgen Schmidhuber, Varun Raj Kompella, Matthew Luciw

Publication date: 23 July 2013

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

Full work available at URL: https://doi.org/10.1162/neco_a_00344

Mathematics Subject Classification ID

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

Related Items (4)

Continual curiosity-driven skill acquisition from high-dimensional video inputs for humanoid robots ⋮ Optimal Curiosity-Driven Modular Incremental Slow Feature Analysis ⋮ Slowness as a Proxy for Temporal Predictability: An Empirical Comparison ⋮ Improved graph-based SFA: information preservation complements the slowness principle

Uses Software

• mdp

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix
• A simplified neuron model as a principal component analyzer
• Neural theory of association and concept-formation
• Independent component analysis, a new concept?
• Sequential extraction of minor components
• Convergence analysis of a simple minor component analysis algorithm
• On the Relation of Slow Feature Analysis and Laplacian Eigenmaps
• Training Products of Experts by Minimizing Contrastive Divergence
• Lanczo's Generalized Derivative
• Slow Feature Analysis: Unsupervised Learning of Invariances
• Learning the parts of objects by non-negative matrix factorization

This page was built for publication: Incremental Slow Feature Analysis: Adaptive Low-Complexity Slow Feature Updating from High-Dimensional Input Streams