This talk will be in person in Luddy 1106 (Dorsey Learning Hall) and virtual.
Luddy School of Informatics, Computing, and Engineering Informatics Colloquium Series
Informatics Colloquium Series:
Abstract: What algorithms power human and animal intelligence? How can we reproduce these algorithms in machines? To address these questions, my lab performs parallel controlled-rearing experiments on animals and machines. Using a video game engine, we raise newborn animals and ‘newborn’ artificial agents in the same visual environments and measure their behavior with the same tasks. By modeling animals as “runnable” artificial agents raised in realistic virtual environments, we can reverse engineer the neural algorithms found in nature. These “naturally intelligent” algorithms are an untapped goldmine for next-generation artificial intelligence systems. In this talk, I will describe our progress reverse engineering collective behavior and object recognition.
Biography: Justin Wood is an associate professor studying the origins and computational foundations of intelligence. He works at the intersection of psychology, neuroscience, and artificial intelligence to understand the learning algorithms that power biological intelligence. Professor Wood has studied the psychological abilities of a range of populations, including human adults, infants, chimpanzees, wild monkeys, and newborn chicks. His research is supported by the National Science Foundation, the James McDonnell Foundation, and Facebook Artificial Intelligence Research.
To register and find more information, see the official IU event page.