NIPS
1997
13 years 7 months ago
1997
In many applications, such as credit default prediction and medical image recognition, test inputs are available in addition to the labeled training examples. We propose a method ...
NIPS
1997
13 years 7 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...
NIPS
1997
13 years 7 months ago
1997
A new algorithm is presented which approximates the perceived visual similarity between images. The images are initially transformed into a feature space which captures visual str...
NIPS
1997
13 years 7 months ago
1997
NIPS
1997
13 years 7 months ago
1997
NIPS
1997
13 years 7 months ago
1997
In many real world tasks, only a small fraction of the available inputs are important at any particular time. This paper presents a method for ascertaining the relevance of inputs...
NIPS
1997
13 years 7 months ago
1997
Prioritized sweeping is a model-based reinforcement learning method that attempts to focus an agent’s limited computational resources to achieve a good estimate of the value of ...
NIPS
1997
13 years 7 months ago
1997
This paper describes some of the interactions of model learning algorithms and planning algorithms we have found in exploring model-based reinforcement learning. The paper focuses...
NIPS
2000
13 years 7 months ago
2000
In theory, the Winnow multiplicative update has certain advantages over the Perceptron additive update when there are many irrelevant attributes. Recently, there has been much eff...
NIPS
2000
13 years 7 months ago
2000
In an important recent paper, Yedidia, Freeman, and Weiss [11] showed that there is a close connection between the belief propagation algorithm for probabilistic inference and the...