Slow Feature Analysis

By Laurenz Wiskott, Pietro Berkes, Mathias Franzius, Henning Sprekeler, Niko Wilbert. 2014

54 citations recorded by the source corpus.

Subfields: Analytical Chemistry, Cognitive Neuroscience

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Analytical Chemistry

1. Chen Wu
2. J. Urgen Schmidhuber
3. Bo Du
4. Matthew D. Luciw
5. Varun Raj Kompella
6. Lixiang Ru
7. Liangpei Zhang

In Cognitive Neuroscience

1. J. Urgen Schmidhuber
2. Chen Wu
3. Bo Du
4. Matthew D. Luciw
5. Varun Raj Kompella
6. Liangpei Zhang
7. Faustino J. Gomez
8. Bill Hibbard

Citations in the corpus

• Deep learning in neural networks: An overview (2014, methodology): “RL combined with UL based on Slow Feature Analysis (Kompella, Luciw, & Schmidhuber, 2012; Wiskott & Sejnowski, 2002) enabled a real humanoid robot to learn skills from raw high-dimensional video streams (Luciw, Kompella, Kazerounian, & Schmidhuber, 2013).”
• Unsupervised Deep Slow Feature Analysis for Change Detection in Multi-Temporal Remote Sensing Images (2018, background): “SFA is a feature learning algorithm that extracts invariant and slowly varying features from input signals [30], [31].”
• Slow Feature Analysis for Change Detection in Multispectral Imagery (2014, background): “Slow feature analysis (SFA) is a new learning algorithm that extracts invariant and slowly varying features from input signals [44], [45].”
• Incremental Slow Feature Analysis: Adaptive Low-Complexity Slow Feature Updating from High-Dimensional Input Streams (2012, methodology): “Slow feature analysis (SFA; Wiskott & Sejnowski, 2002 ; Wiskott, Berkes, Franzius, Sprekeler, & Wilbert, 2011 ) is an unsupervised learning technique that extracts features from an input stream with the objective that the feature responses must change over time but should change as slowly as possi”
• Predictable Feature Analysis (2013, unknown): “[13] describes this procedure in detail.”