Computer Science – Artificial Intelligence
Scientific paper
2011-12-09
Computer Science
Artificial Intelligence
Scientific paper
Slow Feature Analysis (SFA) extracts features representing the underlying causes of changes within a temporally coherent high-dimensional raw sensory input signal. Our novel incremental version of SFA (IncSFA) combines incremental Principal Components Analysis and Minor Components Analysis. Unlike standard batch-based SFA, IncSFA adapts along with non-stationary environments, is amenable to episodic training, is not corrupted by outliers, and is covariance-free. These properties make IncSFA a generally useful unsupervised preprocessor for autonomous learning agents and robots. In IncSFA, the CCIPCA and MCA updates take the form of Hebbian and anti-Hebbian updating, extending the biological plausibility of SFA. In both single node and deep network versions, IncSFA learns to encode its input streams (such as high-dimensional video) by informative slow features representing meaningful abstract environmental properties. It can handle cases where batch SFA fails.
Kompella Varun Raj
Luciw Matthew
Schmidhuber Juergen
No associations
LandOfFree
Incremental Slow Feature Analysis: Adaptive and Episodic Learning from High-Dimensional Input Streams does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Incremental Slow Feature Analysis: Adaptive and Episodic Learning from High-Dimensional Input Streams, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Incremental Slow Feature Analysis: Adaptive and Episodic Learning from High-Dimensional Input Streams will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-44056