ALT

2015

Springer

8 years 5 months ago
2015

Springer

Weighted automata (WFAs) provide a general framework for the representation of functions mapping strings to real numbers. They include as special instances deterministic ﬁnite au...

ALT

2015

Springer

8 years 5 months ago
2015

Springer

Abstract. We introduce a broad learning model formed by cascades of predictors, Deep Cascades, that is structured as general decision trees in which leaf predictors or node questio...

ALT

2015

Springer

8 years 5 months ago
2015

Springer

We consider smoothed versions of geometric range spaces, so an element of the ground set (e.g. a point) can be contained in a range with a non-binary value in [0, 1]. Similar noti...

ALT

2015

Springer

8 years 5 months ago
2015

Springer

Kolmogorov complexity measures the amount of information in data, but does not distinguish structure from noise. Kolmogorov’s deﬁnition of the structure function was the ﬁrs...

ALT

2015

Springer

8 years 5 months ago
2015

Springer

The transformation of a relational database schema into fourth normal form, which minimizes data redundancy, relies on the correct identiﬁcation of multivalued dependencies. In t...

ALT

2015

Springer

8 years 5 months ago
2015

Springer

Dimensionality reduction is a very common preprocessing approach in many machine learning tasks. The goal is to design data representations that on one hand reduce the dimension of...

ALT

2015

Springer

8 years 5 months ago
2015

Springer

We consider an online job scheduling problem on a single machine with precedence constraints under uncertainty. In this problem, for each trial t = 1, . . . , T, the player chooses...

ALT

2015

Springer

8 years 5 months ago
2015

Springer

Abstract. We compose a toolbox for the design of Minimum Disagreement algorithms. This box contains general procedures which transform (without much loss of eﬃciency) algorithms ...

ALT

2015

Springer

8 years 5 months ago
2015

Springer

Deterministic ﬁnite automata (DFA) have long served as a fundamental computational model in the study of theoretical computer science, and the problem of learning a DFA from give...

ALT

2015

Springer

8 years 5 months ago
2015

Springer

We consider a problem of learning kernels for use in SVM classiﬁcation in the multi-task and lifelong scenarios and provide generalization bounds on the error of a large margin c...