Humans recognize visual objects with such ease that it is easy to overlook what an impressive computational feat this represents. Any given object in the world can cast an effectively infinite number of different images onto the retina, depending on its position relative to the viewer, the configuration of light sources, and the presence of other objects in the visual field. In spite of this extreme variation, biological visual systems are able to effortlessly recognize at least hundreds of thousands of distinct object classes—a feat that no current artificial system can come close to achieving.
Our lab is working to understand how biological systems achieve these remarkable abilities. We see this challenge as an exercise in reverse engineering – studying the only known system that can perform robust object recognition, so that we can build artificial systems that can do the same. What we learn along the way will hopefully extend our understanding of how the brain works in general, potentially leading to biomedical advances along the way.