Incremental slow feature analysis

Authors:
Varun Raj Kompella;Matthew Luciw;Jürgen Schmidhuber
Affiliations:
IDSIA, Galleria 2, Switzerland;IDSIA, Galleria 2, Switzerland;IDSIA, Galleria 2, Switzerland
Venue:
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
Year:
2011

Citing 5
Cited 3

Original Contribution: Principal components, minor components, and linear neural networks

Neural Networks
Sequential Extraction of Minor Components

Neural Processing Letters
Slow feature analysis: unsupervised learning of invariances

Neural Computation
Candid Covariance-Free Incremental Principal Component Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Convergence analysis of a simple minor component analysis algorithm

Neural Networks

Incremental slow feature analysis: Adaptive low-complexity slow feature updating from high-dimensional input streams

Neural Computation
Low complexity proto-value function learning from sensory observations with incremental slow feature analysis

ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part II
Incremental slow feature analysis with indefinite kernel for online temporal video segmentation

ACCV'12 Proceedings of the 11th Asian conference on Computer Vision - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Slow Feature Analysis (SFA) unsupervised learning framework extracts features representing the underlying causes of the changes within a temporally coherent high-dimensional raw sensory input signal. We develop the first online version of SFA, via a combination of incremental Principal Components Analysis and Minor Components Analysis. Unlike standard batch-based SFA, online SFA adapts along with non-stationary environments, which makes it a generally useful unsupervised preprocessor for autonomous learning agents. We compare online SFA to batch SFA in several experiments and show that it indeed learns without a teacher to encode the input stream by informative slow features representing meaningful abstract environmental properties. We extend online SFA to deep networks in hierarchical fashion, and use them to successfully extract abstract object position information from high-dimensional video.