Abstract
Mammals rely on vision, audition, and olfaction to remotely sense stimuli in their environment. Determining how the mammalian brain uses this sensory information to recognize objects has been one of the major goals of psychology and neuroscience. Likewise, researchers in computer vision, machine audition, and machine olfaction have endeavored to discover good algorithms for stimulus classification. Almost 50 years ago, the neuroscientist Jerzy Konorski proposed a theoretical model in his final monograph in which competing sets of “gnostic” neurons sitting atop sensory processing hierarchies enabled stimuli to be robustly categorized, despite variations in their presentation. Much of what Konorski hypothesized has been remarkably accurate, and neurons with gnostic-like properties have been discovered in visual, aural, and olfactory brain regions. Surprisingly, there have not been any attempts to directly transform his theoretical model into a computational one. Here, I describe the first computational implementation of Konorski's theory. The model is not domain specific, and it surpasses the best machine learning algorithms on challenging image, music, and olfactory classification tasks, while also being simpler. My results suggest that criticisms of exemplar-based models of object recognition as being computationally intractable due to limited neural resources are unfounded.
Highlights
We can recognize thousands of object categories using our senses [1]
Statistical performance measures consistent with those used in computer vision, machine olfaction, and machine audition were used in my analysis
Konorski proposed a universal theory for recognition across sensory modalities [2]
Summary
We can recognize thousands of object categories using our senses [1]. While our ability to quickly do this seems effortless, computer scientists have yet to construct algorithms that rival our capabilities [1]. While computer scientists have only been working on these problems since the 1960s, our brains have been forged by evolution over millions of years. Our ancestors needed to remotely recognize stimuli using vision, audition, and olfaction to find food, identify mates, and cope with predators. To do these tasks, the mammalian brain hierarchically processes sensory information, enabling stimuli to be classified into general categories despite non-relevant stimulus variation. We can recognize our mother’s face from others despite changes in viewpoint, distinguish between the voices of our friends when they are shouting or whispering, and identify the scent of a mango even as the intensity of its odor varies as it ripens
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
