Differentiable Neural Computers for Memory-Based Control (A Neural Turing Machine)
Dr Greg Wayne, Google Deep Mind
Seminar
Wednesday, 13 January 2016, 1pm to 2pm
CNCB Tinsley Building
Oxford Neurotheory Forum Seminar
"I will describe a neural network control circuit that interfaces to a large, external memory buffer, which it can learn to read from and write to. I will show that this system, called a Differentiable Neural Computer, excels at learning to represent and compute transformations of data structures. It can also learn strictly from task-related reinforcement signals to compute beneficial courses of action. "