Neural Computation and Adaptive Perception
Hidden somewhere in the dense architecture of the human brain is the astounding power to convert the signals flowing along millions of sensory nerve fibres into a coherent model of the world.
Neural Computation and Adaptive Perception aims to unlock the mystery of how our brains convert sensory stimuli into information and to recreate human-style learning in computers. While this group focuses on visual systems, their research also points to broader explanations of how the brain processes other kinds of important information, including sounds, smells and tastes.
Not only has their research provided promising new explanations of how people learn, it has also bolstered efforts to create new artificial visual systems and synthetic neural networks that have brain-like learning capability.
One key to understanding how the brain processes visual information is to determine the algorithm, or computational principle, responsible for brain function. This algorithm can be used to create intelligent devices, such as artificial eyes wired directly into the nervous system, or security surveillance devices at airports that can pick out suspicious objects.
Beyond engineering applications, a deeper understanding of the brain could also provide new understanding of brain diseases such as Parkinson’s and Alzheimer’s. Researchers know that these diseases result when the brain’s algorithms break down, but they are not sure exactly how or why. A better understanding of the brain could help to figure out how to do maintenance on it and help to sustain a high mental quality of life.
Program members have backgrounds in computer science, psychology, electrical and computer engineering, neuroscience, and ophthalmology.
Read more
-
DIRECTOR
Geoffrey Hinton
Geoffrey Hinton received his BA in experimental psychology from Cambridge in 1970 and his PhD in Artificial Intelligence from Edinburgh in 1978. He did postdoctoral work at Sussex University and the University of California San Diego and spent five years as a faculty member in the Computer Science department at Carnegie-Mellon University.
View full profile -
The Teacher in the Machine
CIFAR Member Terry Sejnowski and his collaborators have identified brain machinery that supports perception and action elements of learning. This has opened up the doors for the possibility of personalized pedagogy in the classroom.
Read more