Title |
An intrinsic value system for developing multiple invariant representations with incremental slowness learning
|
---|---|
Published in |
Frontiers in Neurorobotics, January 2013
|
DOI | 10.3389/fnbot.2013.00009 |
Pubmed ID | |
Authors |
Matthew Luciw, Varun Kompella, Sohrob Kazerounian, Juergen Schmidhuber |
Abstract |
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 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. |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Spain | 2 | 3% |
Japan | 1 | 1% |
United Kingdom | 1 | 1% |
United States | 1 | 1% |
Unknown | 63 | 93% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Student > Ph. D. Student | 17 | 25% |
Student > Master | 17 | 25% |
Researcher | 8 | 12% |
Student > Postgraduate | 6 | 9% |
Student > Doctoral Student | 3 | 4% |
Other | 9 | 13% |
Unknown | 8 | 12% |
Readers by discipline | Count | As % |
---|---|---|
Computer Science | 24 | 35% |
Engineering | 15 | 22% |
Psychology | 3 | 4% |
Medicine and Dentistry | 3 | 4% |
Agricultural and Biological Sciences | 3 | 4% |
Other | 9 | 13% |
Unknown | 11 | 16% |