Novelty detection: Difference between revisions
No edit summary |
No edit summary |
||
| Line 3: | Line 3: | ||
Novelty detection is one of the fundamental requirements of a good [[classification in machine learning|classification system]].<ref name="markou"/> A machine learning system can never be trained with all the possible object classes and hence the performance of the network will be poor for those classes that are under-represented in the [[training set]].<ref name="stephen">[http://seat.massey.ac.nz/personal/s.r.marsland/PUBS/NCS.pdf Novelty Detection in Learning Systems.Stephen Marsland, Division of Imaging Science and Biomedical Engineering, Stopford Building, The University of Manchester, Oxford Road, Manchester M13 9PL, UK.]</ref> A good classification system must have the ability to differentiate between known and unknown objects during testing.<ref name="markou"/> For this purpose, different [[Mathematical model|model]]s for novelty detection have been proposed. |
Novelty detection is one of the fundamental requirements of a good [[classification in machine learning|classification system]].<ref name="markou"/> A machine learning system can never be trained with all the possible object classes and hence the performance of the network will be poor for those classes that are under-represented in the [[training set]].<ref name="stephen">[http://seat.massey.ac.nz/personal/s.r.marsland/PUBS/NCS.pdf Novelty Detection in Learning Systems.Stephen Marsland, Division of Imaging Science and Biomedical Engineering, Stopford Building, The University of Manchester, Oxford Road, Manchester M13 9PL, UK.]</ref> A good classification system must have the ability to differentiate between known and unknown objects during testing.<ref name="markou"/> For this purpose, different [[Mathematical model|model]]s for novelty detection have been proposed. |
||
Novelty detection is a hard problem in [[machine learning]] since it depends on the statistics of the already known information |
Novelty detection is a hard problem in [[machine learning]] since it depends on the statistics of the already known information. A generally applicable, parameter-free method for [[outlier]] detection in a high-dimensional space is not yet known. Novelty detection finds a variety of applications especially in [[signal processing]], [[computer vision]], [[pattern recognition]], [[data mining]] and [[robotics]].<ref name="markou"/> Another important application is the detection of a [[disease]] or potential [[Fault (technology)|fault]] whose class may be under-represented in the training set.<ref name="stephen"/> |
||
The statistical approaches to novelty detection may be classified into [[parametric statistics|parametric]] and [[non-parametric]] approaches. Parametric approaches assume a specific statistical distribution (such as a [[Gaussian distribution]]) of data and statistical modeling based on data [[mean]] and [[covariance]], whereas non-parametric approaches do not make any assumption on the statistical properties of data.<ref name="markou"/> |
The statistical approaches to novelty detection may be classified into [[parametric statistics|parametric]] and [[non-parametric]] approaches. Parametric approaches assume a specific statistical distribution (such as a [[Gaussian distribution]]) of data and statistical modeling based on data [[mean]] and [[covariance]], whereas non-parametric approaches do not make any assumption on the statistical properties of data.<ref name="markou"/> |
||
Revision as of 14:08, 12 January 2015
Novelty detection is the identification of new or unknown data that a machine learning system has not been trained with and was not previously aware of,[1] with the help of either statistical or neural network based approaches.
Novelty detection is one of the fundamental requirements of a good classification system.[1] A machine learning system can never be trained with all the possible object classes and hence the performance of the network will be poor for those classes that are under-represented in the training set.[2] A good classification system must have the ability to differentiate between known and unknown objects during testing.[1] For this purpose, different models for novelty detection have been proposed.
Novelty detection is a hard problem in machine learning since it depends on the statistics of the already known information. A generally applicable, parameter-free method for outlier detection in a high-dimensional space is not yet known. Novelty detection finds a variety of applications especially in signal processing, computer vision, pattern recognition, data mining and robotics.[1] Another important application is the detection of a disease or potential fault whose class may be under-represented in the training set.[2]
The statistical approaches to novelty detection may be classified into parametric and non-parametric approaches. Parametric approaches assume a specific statistical distribution (such as a Gaussian distribution) of data and statistical modeling based on data mean and covariance, whereas non-parametric approaches do not make any assumption on the statistical properties of data.[1]
References
- ^ a b c d e M. Markou, S. Singh, Novelty detection: A review, part 1: Statistical approaches, Signal Processing 83, 2481–2497, 2003
- ^ a b Novelty Detection in Learning Systems.Stephen Marsland, Division of Imaging Science and Biomedical Engineering, Stopford Building, The University of Manchester, Oxford Road, Manchester M13 9PL, UK.
 | This computing article is a stub. You can help Wikipedia by expanding it. |