Autonomous learning of abstractions using curiosity-driven modular incremental slow feature analysis

Varun Raj Kompella, Matthew Luciw, Marijn Stollenga, Leo Pape, Jürgen Schmidhuber

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Scopus citations


To autonomously learn behaviors in complex environments, vision-based agents need to develop useful sensory abstractions from high-dimensional video. We propose a modular, curiosity-driven learning system that autonomously learns multiple abstract representations. The policy to build the library of abstractions is adapted through reinforcement learning, and the corresponding abstractions are learned through incremental slow-feature analysis (IncSFA). IncSFA learns each abstraction based on how the inputs change over time, directly from unprocessed visual data. Modularity is induced via a gating system, which also prevents abstraction duplication. The system is driven by a curiosity signal that is based on the learnability of the inputs by the current adaptive module. After the learning completes, the result is multiple slow-feature modules serving as distinct behavior-specific abstractions. Experiments with a simulated iCub humanoid robot show how the proposed method effectively learns a set of abstractions from raw un-preprocessed video, to our knowledge the first curious learning agent to demonstrate this ability. © 2012 IEEE.
Original languageEnglish (US)
Title of host publication2012 IEEE International Conference on Development and Learning and Epigenetic Robotics, ICDL 2012
StatePublished - Dec 1 2012
Externally publishedYes


Dive into the research topics of 'Autonomous learning of abstractions using curiosity-driven modular incremental slow feature analysis'. Together they form a unique fingerprint.

Cite this