An intrinsic value system for developing multiple invariant representations with incremental slowness learning
Open Access
- 31 December 2012
- journal article
- research article
- Published by Frontiers Media SA in Frontiers in Neurorobotics
Abstract
Curiosity Driven Modular Incremental Slow Feature Analysis (CD-MISFA; Kortmella et al., 2012a) 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 discuss computational properties of the CD-MISFA model itself as well as neurophysiological analogs fulfilling similar functional roles. CD-MISFA combines 1. unsupervised representation learning through the slowness principle, 2. generation of an intrinsic reward signal through learning progress of the developing features, and 3. balancing of exploration and exploitation to maximize learning progress and quickly learn multiple feature sets for perceptual simplification. Experimental results on synthetic observations and on the iCub robot show that the intrinsic value system is essential for representation learning. Representations are typically explored and learned in order from least to most costly, as predicted by the theory of curiosity.This publication has 53 references indexed in Scilit:
- PowerPlay: Training an Increasingly General Problem Solver by Continually Searching for the Simplest Still Unsolvable ProblemFrontiers in Psychology, 2013
- In search of the neural circuits of intrinsic motivationFrontiers in Neuroscience, 2007
- Convergence analysis of a simple minor component analysis algorithmNeural Networks, 2007
- Staged Competence Learning in Developmental RoboticsAdaptive Behavior, 2007
- Slowness and Sparseness Lead to Place, Head-Direction, and Spatial-View CellsPLoS Computational Biology, 2007
- Phasic norepinephrine: A neural interrupt signal for unexpected eventsNetwork: Computation in Neural Systems, 2006
- Microstructure of a spatial map in the entorhinal cortexNature, 2005
- Control of exploitation–exploration meta-parameter in reinforcement learningNeural Networks, 2002
- A Neural Substrate of Prediction and RewardScience, 1997
- The hippocampus as a spatial map. Preliminary evidence from unit activity in the freely-moving ratBrain Research, 1971