We present a new approach to reinforcement learning in which the policies considered by the learning process are constrained by hierarchies of partially specified machines. This ...
Up-propagation is an algorithm for inverting and learning neural network generative models. Sensory input is processed by inverting a model that generates patterns from hidden var...
A rich body of data exists showing that recollection of specific information makes an important contribution to recognition memory, which is distinct from the contribution of fam...
Randall C. O'Reilly, Kenneth A. Norman, James L. M...
Program execution speed on modern computers is sensitive, by a factor of two or more, to the order in which instructions are presented to the processor. To realize potential execu...
J. Eliot B. Moss, Paul E. Utgoff, John Cavazos, Do...
Multiple-instance learning is a variation on supervised learning, where the task is to learn a concept given positive and negative bags of instances. Each bag may contain many ins...
Recent imaging studies suggest that object knowledge is stored in the brain as a distributed network of many cortical areas. Motivated by these observations, we study a multi-modu...
We have constructed an inexpensive, video-based, motorized tracking system that learns to track a head. It uses real time graphical user inputs or an auxiliary infrared detector a...
Singular value decomposition (SVD) can be viewed as a method for unsupervised training of a network that associates two classes of events reciprocally by linear connections throug...