An intrinsic value system for developing multiple invariant representations with incremental slowness learning
Curiosity Driven Modular Incremental Slow Feature Analysis (CD-MISFA;) is a recently introduced model of intrinsically-motivated invariance learning. Artificial curiosity enables the orderly formation of multiple stable sensory representations to simplify the agent's complex sensory input. We d...
Main Authors: | Luciw, Matthew, Kompella, Varun, Kazerounian, Sohrob, Schmidhuber, Juergen |
---|---|
Format: | Online |
Language: | English |
Published: |
Frontiers Media S.A.
2013
|
Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3667249/ |
Similar Items
-
Real-time learning of predictive recognition categories that chunk sequences of items stored in working memory
by: Kazerounian, Sohrob, et al.
Published: (2014) -
Incremental learning of skill collections based on intrinsic motivation
by: Metzen, Jan H., et al.
Published: (2013) -
Where-what networks for motor invariance without any internal master map
by: Weng, Juyang, et al.
Published: (2010) -
Confidence-based progress-driven self-generated goals for skill acquisition in developmental robots
by: Ngo, Hung, et al.
Published: (2013) -
Invariants Discretization for Individuality Representation in Handwritten Authorship
by: Muda, A. K., et al.
Published: (2008)