TY - GEN
T1 - Towards learning strategies and exploration patterns for feature perception
AU - Lewkowicz, Daniel
AU - Giagkos, Alexandros
AU - Shaw, Patricia
AU - Kumar, Suresh
AU - Lee, Mark
AU - Shen, Qiang
PY - 2017/2/7
Y1 - 2017/2/7
N2 - During infancy, infants spend a lot of time visually exploring the scene around them. Over the first year of life, the level of detail that can be perceived visually increases significantly. In this study, the ability to perceive areas of interest w.r.t. human developmental change in vision, specifically acuity and field of view over the first year of life, is investigated. Two scenarios, namely learning through a series of developmental changes and learning without any constraints, shed light on how a humanoid robot scaffolds learning of interesting areas in the scene through different emergent exploratory behaviours. Divergence/convergence in features is reported, demonstrating a potential to be used at a higher level of understanding. Staged strategies with early sensory constraints and exploratory behaviour based on 'similarity searches' improve the quality of acquired features and may be used as a mechanism for better on-line learning of objects knowledge.
AB - During infancy, infants spend a lot of time visually exploring the scene around them. Over the first year of life, the level of detail that can be perceived visually increases significantly. In this study, the ability to perceive areas of interest w.r.t. human developmental change in vision, specifically acuity and field of view over the first year of life, is investigated. Two scenarios, namely learning through a series of developmental changes and learning without any constraints, shed light on how a humanoid robot scaffolds learning of interesting areas in the scene through different emergent exploratory behaviours. Divergence/convergence in features is reported, demonstrating a potential to be used at a higher level of understanding. Staged strategies with early sensory constraints and exploratory behaviour based on 'similarity searches' improve the quality of acquired features and may be used as a mechanism for better on-line learning of objects knowledge.
UR - http://www.scopus.com/inward/record.url?scp=85015334816&partnerID=8YFLogxK
UR - https://ieeexplore.ieee.org/document/7846832
U2 - 10.1109/DEVLRN.2016.7846832
DO - 10.1109/DEVLRN.2016.7846832
M3 - Conference publication
AN - SCOPUS:85015334816
SN - 978-1-5090-5070-3
T3 - 2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2016
SP - 278
EP - 283
BT - 2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2016
PB - IEEE
T2 - 2016 Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob 2016
Y2 - 19 September 2016 through 22 September 2016
ER -