Stephen Grossberg

Affiliation

Center for Adaptive Systems, Graduate Program in Cognitive and Neural Systems
Center for Computational Neuroscience and Neural Technology
Departments of Mathematics,  Psychology, and Biomedical Engineering, Boston University

Title: From active 3D vision to invariant object and scene search, learning, and recognition

Abstract : How do we learn what a visually seen object is? How do our brains learn without supervision to link multiple views of the same object into an invariant object category while our eyes search a scene, even before we have a concept of the object? Indeed, why do we not link together views of different objects when there is no teacher to correct us? Why do not our eyes move around randomly? How do they explore interesting features of novel objects and thereby enable us to learn view-, size-, and positionally-invariant object categories? How do representations of a scene remain binocularly fused as our eyes explore it? How is the gist of a scene computed? How do we solve the Where’s Waldo problem and thereby efficiently search for desired objects in a scene using object and spatial contextual information? This talk will summarize the ARTSCAN family of neural models that clarifies how the brain solves these problems in a unified way by coordinating processes of 3D vision and figure-ground separation, spatial and object attention, object and scene category learning, predictive remapping, and eye movement search. ARTSCAN illustrates revolutionary new computational paradigms whereby the brain computes: Complementary Computing clarifies the nature of brain specialization, and Laminar Computing clarifies why all neocortical circuits exhibit a layered architecture. ARTSCAN also provides unified explanations and simulations of brain and behavioral data, and computer simulation benchmarks that support the model, which provides a blueprint for developing a new type of system for active vision and autonomous learning and recognition.

Biography: Stephen Grossberg is Wang Professor of Cognitive and Neural Systems; Professor of Mathematics, Psychology, and Biomedical Engineering; and Director of the Center for Adaptive Systems at Boston University. He is a principal founder and current research leader in computational neuroscience, connectionist cognitive science, and neuromorphic technology. Grossberg introduced the paradigm of using nonlinear systems of differential equations to model how brain mechanisms give rise to behavioral functions. In 1957-1958, he introduced widely used equations for short-term memory (STM), or neuronal activation; medium-term memory (MTM), or activity-dependent habituation; and long-term memory (LTM), or neuronal learning. His work focuses upon how individuals adapt autonomously in real-time to unexpected environmental challenges, and includes models of vision and visual cognition; object, scene, and event recognition; audition, speech and language; development; cognitive information processing; reinforcement learning and cognitive-emotional interactions; navigation; social cognition; sensory-motor control and planning; mental disorders; and neuromorphic technology. Grossberg founded key infrastructure of the field of neural networks, including the International Neural Network Society and the journal Neural Networks. He is a fellow of AERA, APA, APS, IEEE, INNS, MDRS, and SEP. He has published 17 books or journal special issues, over 500 research articles, and has 7 patents. See the following web pages for further information:

http://cns.bu.edu/~steve
http://en.wikipedia.org/wiki/Stephen_Grossberg
http://cns.bu.edu/~steve/GrossbergNNeditorial2010.pdf