1997 search results - page 249 / 400 » On the convergence of Hill's method |
113
click to vote
UAI
1998
15 years 2 months ago
1998
We present an anytime algorithm which computes policies for decision problems represented as multi-stage influence diagrams. Our algorithm constructs policies incrementally, start...
107
click to vote
WSC
2000
15 years 2 months ago
2000
This paper introduced the application of a more efficient mathematical representation of the kinematics of avatars, or digital human beings, in telecollaborative virtual reality e...
115
click to vote
NIPS
1996
15 years 2 months ago
1996
In this paper we apply the method of complexity regularization to derive estimation bounds for nonlinear function estimation using a single hidden layer radial basis function netwo...
NIPS
1996
15 years 2 months ago
1996
In pattern recognition, statistical modeling, or regression, the amount of data is a critical factor affecting the performance. If the amount of data and computational resources ar...
110
click to vote
NIPS
1996
15 years 2 months ago
1996
Abstract. In this paper we investigate the feed-forward learning problem. The well-known ill-conditioning which is present in most feed-forward learning problems is shown to be the...