NIPS
2001
13 years 5 months ago
2001
We show that states of a dynamical system can be usefully represented by multi-step, action-conditional predictions of future observations. State representations that are grounded...
NIPS
2001
13 years 5 months ago
2001
We combine the replica approach from statistical physics with a variational approach to analyze learning curves analytically. We apply the method to Gaussian process regression. A...
NIPS
2001
13 years 5 months ago
2001
NIPS
2001
13 years 5 months ago
2001
We derive an equivalence between AdaBoost and the dual of a convex optimization problem, showing that the only difference between minimizing the exponential loss used by AdaBoost ...
NIPS
2001
13 years 5 months ago
2001
With the increasing number of users of mobile computing devices (e.g. personal digital assistants) and the advent of third generation mobile phones, wireless communications are be...
NIPS
2001
13 years 5 months ago
2001
We present a new approach to bounding the true error rate of a continuous valued classifier based upon PAC-Bayes bounds. The method first constructs a distribution over classifier...
NIPS
2001
13 years 5 months ago
2001
When constructing a classifier, the probability of correct classification of future data points should be maximized. In the current paper this desideratum is translated in a very ...
NIPS
2001
13 years 5 months ago
2001
We propose a new approach to reinforcement learning which combines least squares function approximation with policy iteration. Our method is model-free and completely off policy. ...
NIPS
2001
13 years 5 months ago
2001
We give results about the learnability and required complexity of logical formulae to solve classification problems. These results are obtained by linking propositional logic with...
NIPS
2001
13 years 5 months ago
2001
Tangential hand velocity profiles of rapid human arm movements often appear as sequences of several bell-shaped acceleration-deceleration phases called submovements or movement un...