Title: Rapidly and Reliably Recognizing an Object

Speaker: Minjoon Kouh, Von Neumann Fellowship Interview Candidate, Massachusetts Institute
of Technology

Date/Time: Monday, January 8, 2007, 9:00am – 10:00am

Location: CSRI Building, Room 90 (Sandia NM)

Brief Abstract: Rapidly and reliably recognizing an object (is that a cat or a tiger?) is obviously an important skill for survival. However, it is a difficult computational problem, because the same object can appear differently under various conditions, while different objects can share similar features. A robust recognition system must have a capacity to distinguish between similar-looking objects, while being invariant to the appearance-altering transformation of an object. The fundamental challenge for any recognition system (whether it is in vision, audition or olfaction) lies within this simultaneous requirement for both specificity and invariance. An emerging picture from decades of neuroscience research is that the cortex overcomes this challenge by gradually building up specificity and invariance with a hierarchical architecture. I will present a biologically-inspired, hierarchical model of the primate visual cortex, which is capable of explaining the observed neural properties and performing visual object recognition tasks. I will also show that a canonical neural circuitry, composed of relatively simple excitatory and inhibitory elements, may operate throughout the hierarchy of cortical areas and satisfy the critical requirements for specificity and invariance.

CSRI POC: Jean-Paul Watson, (505) 845-8887