Evgueni N. Smirnov

Learn More
We address the problem of applying machine-learning classifiers in domains where incorrect classifications have severe consequences. In these domains we propose to apply classifiers only when their performance can be defined by the domain expert prior to classification. The classifiers so obtained are called reliable classifiers. In the article we present(More)
The authors propose a meta-typicalness approach to apply the typicalness framework for any type of classifiers. The approach can be used to construct classifiers with specified classification performance. Experiments show that the approach results in classifiers that can outperform an existing typicalness-based classifier
This paper proposes a new approach to classification reliability. The key idea is to maintain version spaces containing (close approximations of) the target classifiers. In this way the unanimous-voting rule applied on these version spaces outputs reliable instance classifications. Version spaces are defined in a hypothesis space of oriented hyperplanes.(More)
This paper develops an efficient approach to analytical learning of Asymmetric Stochastic Volatility (ASV) models through nonlinear filtering, and shows that they are useful for practical risk management. This involves the derivation of a Nonlinear Quadrature Filter (NQF) that operates directly on the nonlinear ASV model. The NQF filter makes Gaussian(More)
Instance retraction is a difficult problem for concept learning by version spaces. In this paper, two new version-space representations are introduced: instance-based maximal boundary sets and instancebased minimal boundary sets. They are correct representations for the class of admissible concept languages and are efficiently computable. Compared to other(More)
The task of reliable classification is to determine if a particular instance classification is reliable. There exist two approaches to the task: the Bayesian framework [3] and the typicalness framework [5]. Although both frameworks are useful, the Bayesian framework can be misleading and the typicalness framework is classifier dependent. To overcome these(More)
Reliable classifiers abstain from uncertain instance classifications. In this paper we extend our previous approach to construct reliable classifiers which is based on isometrics in Receiver Operator Characteristic (ROC) space. We analyze the conditions to obtain a reliable classifier with higher performance than previously possible. Our results show that(More)