From supervised to unsupervised support vector machines and applications in astronomy

TY - JOUR

T1 - From supervised to unsupervised support vector machines and applications in astronomy

AU - Gieseke, Fabian

PY - 2013/8/1

Y1 - 2013/8/1

N2 - Support vector machines are among the most popular techniques in machine learning. Given sufficient labeled data, they often yield excellent results. However, for a variety of real-world tasks, the acquisition of sufficient labeled data can be very time-consuming; unlabeled data, on the other hand, can often be obtained easily in huge quantities. Semi-supervised support vector machines try to take advantage of these additional unlabeled patterns and have been successfully applied in this context. However, they induce a hard combinatorial optimization problem. In this work, we present two optimization strategies that address this task and evaluate the potential of the resulting implementations on real-world data sets, including an example from the field of astronomy.

AB - Support vector machines are among the most popular techniques in machine learning. Given sufficient labeled data, they often yield excellent results. However, for a variety of real-world tasks, the acquisition of sufficient labeled data can be very time-consuming; unlabeled data, on the other hand, can often be obtained easily in huge quantities. Semi-supervised support vector machines try to take advantage of these additional unlabeled patterns and have been successfully applied in this context. However, they induce a hard combinatorial optimization problem. In this work, we present two optimization strategies that address this task and evaluate the potential of the resulting implementations on real-world data sets, including an example from the field of astronomy.

U2 - 10.1007/s13218-013-0248-1

DO - 10.1007/s13218-013-0248-1

M3 - Journal article

SN - 0933-1875

VL - 27

SP - 281

EP - 285

JO - Kuenstliche Intelligenz

JF - Kuenstliche Intelligenz

IS - 3

ER -