Searching for authors named "Christos Dimitrakakis" – sorted by Relevance.
11 documents found, showing 1 through 10.
Next 10 →
-
Online Statistical Estimation for Vehicle Control
- …This tutorial examines simple physical models of vehicle dynamics and overviews methods for parameter estimation and control. Firstly, techniques for the estimation of parameters that deal with constraints are detailed. Secondly, methods for controlling the system are explained.…
- Add To MetaCart
-
Online Policy Adaption for Ensemble Algorithms
- …Ensemble algorithms are general methods for improving the performance of a given learning algorithm. This is achieved by the combination of multiple base classi ers into an ensemble.…
- Add To MetaCart
-
Online Policy Adaptation for Ensemble Classifiers
- …Ensemble algorithms can improve the performance of a given learning algorithm through the combination of multiple base classifiers into an ensemble. In this paper, the idea of using an adaptive policy for training and combining the base classifiers is put forward. The e#ectiveness of this approa…
- Cited by 4 (3 self) – Add To MetaCart
-
Gradient Estimates of Return
- …The exploration-exploitation trade-o# that arises when one considers simple point estimates of expected returns no longer appears when full distributions are considered. This work develops a simple gradient-based approach for mainting such distributions and investigates methods for using them to …
- Cited by 1 (1 self) – Add To MetaCart
-
Gradient-Based Estimates of Return Distributions
- …We present a general method for maintaining estimates of the distribution of parameters in arbitrary models. This is then applied to the estimation of probability distributions over actions in value-based reinforcement learning. While this approach is similar to other techniques that maintain a …
- Cited by 2 (2 self) – Add To MetaCart
-
Boosting HMMs with an Application to Speech Recognition
- …Boosting is a general method for training an ensemble of classifiers with a view to improving performance relative to that of a single classifier. While the original AdaBoost algorithm has been defined for classification tasks, the current work examines its applicability to sequence learning problem…
- Cited by 11 (3 self) – Add To MetaCart
-
Boosting Word Error Rates
- …We apply boosting techniques to the problem of word error rate minimisation in speech recognition. This is achieved through a new definition of sample error for boosting and a training procedure for hidden Markov models. For this purpose we define a sample error for sentence examples related to the …
- Cited by 3 (2 self) – Add To MetaCart
-
Online Adaptive Policies for Ensemble Classifiers
- …Ensemble algorithms can improve the performance of a given learning algorithm through the combination of multiple base classifiers into an ensemble. In this paper we attempt to train and combine the base classifiers using an adaptive policy. This policy is learnt through a Q-learning inspired techni…
- Cited by 2 (0 self) – Add To MetaCart
-
Online Policy Adaptation for Ensemble Classifiers
- …Abstract. Ensemble algorithms can improve the performance of a given learning algorithm through the combination of multiple base classifiers into an ensemble. In this paper, the idea of using an adaptive policy for training and combining the base classifiers is put forward. The effectiveness of this…
- Add To MetaCart
-
Estimated of Parameter Distributions for . . .
- …this paper we only present preliminary results on n-armed bandit problems. Although our method is applicable to other tasks and is compatible with eligibility traces, we find that bandit tasks represent a problem that our method should be able to deal with e#ectively and which are easy to analyse. I…
- Add To MetaCart
Showing 1 through 10.
Next 10 →
