Daniel L. Yamins

In the course of everyday functioning, animals (including humans) are constantly faced with real-world environments in which they are required to shift unpredictably between multiple, sometimes unfamiliar, tasks. But how brains support this rapid adaptation of decision making schema, and how they allocate resources towards learning novel tasks is largely unknown both neuroscientifically and algorithmically.

In order to reach the level of intelligence that humans possess, artificial agents need to be able to autonomously interact with other agents and humans and build rich models of how other minds work as a result of these interactions.

Dr. Daniel Bear propose to augment state-of-the-art neural networks with two biologically-inspired properties: the ability to represent the physical world as it changes over time and the ability to learn from self-created signals rather than explicit human instruction.