Improved graph-based SFA: information preservation complements the slowness principle

@article{Escalante2019ImprovedGS,
  title={Improved graph-based SFA: information preservation complements the slowness principle},
  author={Alberto N. Escalante and Laurenz Wiskott},
  journal={Machine Learning},
  year={2019},
  volume={109},
  pages={999-1037}
}
  • Alberto N. Escalante, Laurenz Wiskott
  • Published 2019
  • Computer Science, Mathematics
  • Machine Learning
  • Slow feature analysis (SFA) is an unsupervised learning algorithm that extracts slowly varying features from a multi-dimensional time series. SFA has been extended to supervised learning (classification and regression) by an algorithm called graph-based SFA (GSFA). GSFA relies on a particular graph structure to extract features that preserve label similarities. Processing of high dimensional input data (e.g., images) is feasible via hierarchical GSFA (HGSFA), resulting in a multi-layer neural… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-8 OF 8 CITATIONS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 80 REFERENCES

    Heuristic Evaluation of Expansions for Non-linear Hierarchical Slow Feature Analysis

    Patch Alignment for Dimensionality Reduction

    VIEW 2 EXCERPTS

    On the Relation of Slow Feature Analysis and Laplacian Eigenmaps

    VIEW 1 EXCERPT

    Slow Feature Analysis: Unsupervised Learning of Invariances

    VIEW 4 EXCERPTS

    Densely Connected Convolutional Networks