Skull-closed autonomous development

Authors:
Yuekai Wang;Xiaofeng Wu;Juyang Weng
Affiliations:
State Key Lab. of ASIC & System, Fudan University, Shanghai, China;State Key Lab. of ASIC & System, Fudan University, Shanghai, China;School of Computer Science, Fudan University, Shanghai, China
Venue:
ICONIP'11 Proceedings of the 18th international conference on Neural Information Processing - Volume Part I
Year:
2011

Citing 2
Cited 1

Image Parsing: Unifying Segmentation, Detection, and Recognition

International Journal of Computer Vision
Top–Down Connections in Self-Organizing Hebbian Networks: Topographic Class Grouping

IEEE Transactions on Autonomous Mental Development

Skull-closed autonomous development: object-wise incremental learning

ISNN'12 Proceedings of the 9th international conference on Advances in Neural Networks - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

It seems how the brain develops its representations inside its closed skull throughout the lifetime, while the child incrementally learns one new task after another. By closed skull, we mean that the brain (or the Central Nervous System) inside the skull is off limit to the teachers in the external environment, except its sensory ends and the motor ends. We present Where-What Network (WWN) 6, which has realized our goal of a fully developmental network with closed skull, which means that the human programmer is not allowed to handcraft the internal representation for any concepts about extra-body concepts. We present how the developmental program (DP) of WWN-6 enables the network to learn and perform for attending and recognizing objects in complex backgrounds while the skull is closed.