Where-What Network 3: Developmental top-down attention for multiple foregrounds and complex backgrounds

The Where-What Network 3 (WWN-3) is an artificial developmental network modeled after visual cortical pathways, for the purpose of attention and recognition in the presence of complex natural backgrounds. It is general-purpose and not pre-determined to detect a certain type of stimulus. It is a learning network, which develops its weights from images using a supervised paradigm and a local Hebbian learning algorithm. Attention has been thought of as bottom-up or top-down. This paper focuses on the biologically-inspired mechanisms of top-down attention in WWN-3, through top-down excitation that interacts with bottom-up activity at every layer within the network. Top-down excitation in WWN-3 can control the location of attention by imposing a certain location or disengaging from the current location. It can also control what type of object to search for. Paired layers and sparse coding deal with potential hallucination problems. Top-down attention in WWN occurs as soon as an action emerges at a motor layer, which could be imposed by a teacher or internally selected. Given two competing foregrounds in the same scene, WWN showed effective performance in all the attention modes tested.

[1]  Bärbel Mertsching,et al.  Data- and Model-Driven Gaze Control for an Active-Vision System , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  J. Bullier.  Hierarchies of Cortical Areas , 2003 .

[3]  M. V. Velzen,et al.  Self-organizing maps , 2007 .

[4]  Anne Treisman,et al.  Monitoring and storage of irrelevant messages in selective attention , 1964 .

[5]  John G. Taylor,et al.  CODAM: A neural network model of consciousness , 2007, Neural Networks.

[6]  A. Treisman,et al.  A feature-integration theory of attention , 1980, Cognitive Psychology.

[7]  Juyang Weng,et al.  Where-what network 1: “Where” and “what” assist each other through top-down connections , 2008, 2008 7th IEEE International Conference on Development and Learning.

[8]  C. Koch,et al.  Computational modelling of visual attention , 2001, Nature Reviews Neuroscience.

[9]  Thomas Serre,et al.  Robust Object Recognition with Cortex-Like Mechanisms , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Dileep George,et al.  Towards a Mathematical Theory of Cortical Micro-circuits , 2009, PLoS Comput. Biol..

[11]  John K. Tsotsos,et al.  Modeling Visual Attention via Selective Tuning , 1995, Artif. Intell..

[12]  Matthew H. Wilder.  A Unified Theory of Exogenous and Endogenous Attentional Control , 2008 .

[13]  E. Rolls,et al.  A Neurodynamical cortical model of visual attention and invariant object recognition , 2004, Vision Research.

[14]  John G. Taylor,et al.  The CODAM model of attention and consciousness , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[15]  D. V. van Essen,et al.  A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information , 1993, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[16]  E. Callaway.  Local circuits in primary visual cortex of the macaque monkey. , 1998, Annual review of neuroscience.

[17]  D. G. MacKay.  Aspects of the Theory of Comprehension, Memory and Attention , 1973 .

[18]  Juyang Weng,et al.  2008 Special issue , 2008 .

[19]  Juyang Weng,et al.  Developmental Stereo: Emergence of Disparity Preference in Models of the Visual Cortex , 2009, IEEE Transactions on Autonomous Mental Development.

[20]  Juyang Weng,et al.  Topographic Class Grouping with applications to 3D object recognition , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[21]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[22]  S. Grossberg,et al.  View-invariant object category learning, recognition, and search: How spatial and object attention are coordinated using surface-based attentional shrouds , 2009, Cognitive Psychology.

[23]  J. Deutsch.  Perception and Communication , 1958, Nature.

[24]  G. Deco,et al.  A hierarchical neural system with attentional top–down enhancement of the spatial resolution for object recognition , 2000, Vision Research.

[25]  Juyang Weng,et al.  Dually Optimal Neuronal Layers: Lobe Component Analysis , 2009, IEEE Transactions on Autonomous Mental Development.