46 search results - page 9 / 10 » nips 1996 |
103
click to vote
NIPS
1996
15 years 1 months ago
1996
Dynamic Programming, Q-learning and other discrete Markov Decision Process solvers can be applied to continuous d-dimensional state-spaces by quantizing the state space into an arr...
109
click to vote
NIPS
1996
15 years 1 months ago
1996
Predictions oflifetimesofdynamicallyallocated objects can be used to improve time and space e ciency of dynamic memory management in computer programs. Barrett and Zorn 1993] used...
NIPS
1996
15 years 1 months ago
1996
We present a connectionist method for representing images that explicitlyaddresses their hierarchicalnature. It blends data fromneuroscience about whole-object viewpoint sensitive...
104
click to vote
NIPS
1996
15 years 1 months ago
1996
In the square linear blind source separation problem, one must nd a linear unmixing operator which can detangle the result xi(t) of mixing n unknown independent sources si(t) thro...
NIPS
1996
15 years 1 months ago
1996
A general feature of the cerebral cortex is its massive interconnectivity-ithas been estimatedanatomically 15 that cortical neurons receive on the order of 10,000 synapses, the ma...