108
Voted
NIPS
1997
15 years 5 months ago
1997
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 ...
130
Voted
NIPS
1997
15 years 5 months ago
1997
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...
87
Voted
NIPS
1997
15 years 5 months ago
1997
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...
136
Voted
NIPS
1997
15 years 5 months ago
1997
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...
141
Voted
NIPS
1997
15 years 5 months ago
1997
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...
85
Voted
NIPS
1997
15 years 5 months ago
1997
92
Voted
NIPS
1997
15 years 5 months ago
1997
130
Voted
NIPS
1997
15 years 5 months ago
1997
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...
156
Voted
NIPS
1997
15 years 5 months ago
1997
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...
120
Voted
NIPS
1997
15 years 5 months ago
1997
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...