AbstractThis paper reviews some theoretical and experimental developments in building computable approximations of Kolmogorov's algorithmic notion of randomness. Based on these approximations a new set of machine learning algorithms have been developed that can be used not just to make predictions but also to estimate the confidence under the usual iid assumption
The talk reviews a modern machine learning technique called Conformal Predictors. The approach has b...
AbstractThis paper studies sequence prediction based on the monotone Kolmogorov complexity Km=-logm,...
In this paper we investigate a new formal model of machine learning in which the concept (Boolean fu...
AbstractThis paper reviews some theoretical and experimental developments in building computable app...
Machine-learning classiers are difficult to apply in application domains where incorrect predictions...
Item does not contain fulltextMachine-learning classiers are difficult to apply in application domai...
In this paper we propose a new algorithm for providing confidence and credibility values for predict...
Kernel methods and neural networks are two important schemes in the supervised learning field. The t...
Algorithmic statistics considers the following problem: given a binary string x (e.g., some experime...
Many existing procedures in machine learning and statistics are computationally intractable in the s...
Much of econometrics is based on a tight probabilistic approach to empirical modeling that dates bac...
This and a companion paper propose techniques for constructing parametric mathematical models descri...
This paper studies sequence prediction based on the monotone Kolmogorov complexity Km = − log m, i.e...
- Reinforcement rate of technics and appositeness towards the convenience of the human being is a ...
The talk reviews a modern machine learning technique called Conformal Predictors. The approach has b...
The talk reviews a modern machine learning technique called Conformal Predictors. The approach has b...
AbstractThis paper studies sequence prediction based on the monotone Kolmogorov complexity Km=-logm,...
In this paper we investigate a new formal model of machine learning in which the concept (Boolean fu...
AbstractThis paper reviews some theoretical and experimental developments in building computable app...
Machine-learning classiers are difficult to apply in application domains where incorrect predictions...
Item does not contain fulltextMachine-learning classiers are difficult to apply in application domai...
In this paper we propose a new algorithm for providing confidence and credibility values for predict...
Kernel methods and neural networks are two important schemes in the supervised learning field. The t...
Algorithmic statistics considers the following problem: given a binary string x (e.g., some experime...
Many existing procedures in machine learning and statistics are computationally intractable in the s...
Much of econometrics is based on a tight probabilistic approach to empirical modeling that dates bac...
This and a companion paper propose techniques for constructing parametric mathematical models descri...
This paper studies sequence prediction based on the monotone Kolmogorov complexity Km = − log m, i.e...
- Reinforcement rate of technics and appositeness towards the convenience of the human being is a ...
The talk reviews a modern machine learning technique called Conformal Predictors. The approach has b...
The talk reviews a modern machine learning technique called Conformal Predictors. The approach has b...
AbstractThis paper studies sequence prediction based on the monotone Kolmogorov complexity Km=-logm,...
In this paper we investigate a new formal model of machine learning in which the concept (Boolean fu...
DOI
Add to ORKG