995 search results - page 60 / 199 » nips 2007 |
NIPS
2000
15 years 1 months ago
2000
For many problems which would be natural for reinforcement learning, the reward signal is not a single scalar value but has multiple scalar components. Examples of such problems i...
88
Voted
NIPS
2000
15 years 1 months ago
2000
We have developed a silicon neuron that is inspired by a mathematical model of the leech heartbeat (HN) interneuron. The temporal and ionic current behaviors of this silicon neuro...
102
Voted
NIPS
2000
15 years 1 months ago
2000
We use graphical models to explore the question of how people learn simple causal relationships from data. The two leading psychological theories can both be seen as estimating th...
100
click to vote
NIPS
2000
15 years 1 months ago
2000
We introduce a method of feature selection for Support Vector Machines. The method is based upon finding those features which minimize bounds on the leave-one-out error. This sear...
133
Voted
NIPS
1997
15 years 1 months ago
1997
The observed distribution of natural images is far from uniform. On the contrary, real images have complex and important structure that can be exploited for image processing, reco...