Incremental Slow Feature Analysis

Kompella, Varun Raj; Luciw, Matthew D.; Schmidhuber, Jürgen

doi:10.5591/978-1-57735-516-8/IJCAI11-229

Incremental Slow Feature Analysis

Varun Raj Kompella, Matthew D. Luciw, Jürgen Schmidhuber

Download BibTeX Cite

Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence. Pages 1354-1358.

https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-229

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.

Varun Raj Kompella, Matthew D. Luciw, and Jürgen Schmidhuber. 2011. Incremental Slow Feature Analysis. In Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11. IJCAI, 1354–1358. https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-229

@inproceedings{ijcai2011p229,
  title     = {Incremental Slow Feature Analysis},
  author    = {Kompella, Varun Raj and Luciw, Matthew D. and Schmidhuber, Jürgen},
  booktitle = {Proceedings of the Twenty-Second International Joint Conference on
               Artificial Intelligence, {IJCAI-11}},
  publisher = {AAAI Press/International Joint Conferences on Artificial Intelligence},
  editor    = {Toby Walsh},
  pages     = {1354--1358},
  year      = {2011},
  month     = {7},
  doi       = {10.5591/978-1-57735-516-8/IJCAI11-229},
  url       = {https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-229},
}

TY  - CPAPER
TI  - Incremental Slow Feature Analysis
AU  - Kompella, Varun Raj
AU  - Luciw, Matthew D.
AU  - Schmidhuber, Jürgen
T2  - Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI-11
PB  - AAAI Press/International Joint Conferences on Artificial Intelligence
PY  - 2011
SP  - 1354
EP  - 1358
DO  - 10.5591/978-1-57735-516-8/IJCAI11-229
UR  - https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-229
ER  -