Show simple item record

dc.contributor.author
Bermúdez-Chacón, Róger
dc.contributor.author
Gonnet, Gaston H.
dc.contributor.author
Smith, Kevin
dc.date.accessioned
2018-01-31T06:56:20Z
dc.date.available
2017-06-11T21:33:30Z
dc.date.available
2017-11-24T15:25:14Z
dc.date.available
2018-01-31T06:56:20Z
dc.date.issued
2015
dc.identifier.uri
http://hdl.handle.net/20.500.11850/107673
dc.identifier.doi
10.3929/ethz-a-010558061
dc.description.abstract
The use of machine learning techniques has become increasingly widespread in commercial applications and academic research. Machine learning algorithms learn a model from data that allows computers to make and improve predictions or behaviors. Despite their popularity and usefulness, most machine learning techniques require expert knowledge to guide the decisions about the most appropriate model and settings for a particular problem. In many cases, expert knowledge is not readily available. When it is, the complexity of the problem and subjectivity of the expert can often lead to sub-optimal choices in the machine learning strategy.<br/> Since different machine learning techniques are suitable for different problems, choosing the right technique and fine-tuning its particular settings are crucial tasks that will directly impact the quality of the predictions. However, deciding which machine learning technique is most well suited for processing specific data is not an easy task, as the number of choices is usually very large.<br/> In this work, we present a method that automatically selects the best machine learning algorithm for a particular set of data, and optimizes its parameter settings. Our approach is flexible and customizable, enabling the user to specify their needs in terms of predictive power, sensitivity, specificity, consistency of the predictions, and speed, among other criteria. The results obtained show that using the machine learning technique and configuration sug- gested by our automated approach yields predictions of a much higher quality than selecting the technique with the best results under its default settings. We also present a method to efficiently guide the search for optimal parameter settings by identifying ranges of values for each setting that produce good results for most problems. By transferring this knowledge to new problems, it is possible to find the optimal configuration of the algorithm more quickly.
en_US
dc.language.iso
en
en_US
dc.publisher
ETH-Zürich
en_US
dc.rights.uri
http://rightsstatements.org/page/InC-NC/1.0/
dc.subject
DYNAMIC PROGRAMMING (OPERATIONS RESEARCH)
en_US
dc.subject
MACHINE LEARNING (ARTIFICIAL INTELLIGENCE)
en_US
dc.subject
DYNAMISCHE OPTIMIERUNG (OPERATIONS RESEARCH)
en_US
dc.subject
MASCHINELLES LERNEN (KÜNSTLICHE INTELLIGENZ)
en_US
dc.subject
SUPERVISED LEARNING (ARTIFICIAL INTELLIGENCE)
en_US
dc.subject
ÜBERWACHTES LERNEN (KÜNSTLICHE INTELLIGENZ)
en_US
dc.subject
Hyperparameter optimization
en_US
dc.subject
Supervised Machine Learning
en_US
dc.subject
Model selection
en_US
dc.title
Automatic problem-specific hyperparameter optimization and model selection for supervised machine learning: Technical Report
en_US
dc.type
Report
dc.rights.license
In Copyright - Non-Commercial Use Permitted
dc.date.published
2015
ethz.title.subtitle
Technical Report
en_US
ethz.size
52 p.
en_US
ethz.code.ddc
0 - Computer science, information & general works::004 - Data processing, computer science
en_US
ethz.identifier.nebis
010558061
ethz.publication.place
Zürich
en_US
ethz.publication.status
published
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02150 - Dep. Informatik / Dep. of Computer Science
en_US
ethz.date.deposited
2017-06-11T21:34:01Z
ethz.source
ECOL
ethz.source
ECIT
ethz.identifier.importid
imp593653bfec1d456405
ethz.identifier.importid
imp59366b8180d2e28245
ethz.ecolpid
eth:48308
ethz.ecitpid
pub:168281
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2017-07-12T15:34:45Z
ethz.rosetta.lastUpdated
2018-11-06T07:41:18Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&amp;rft_val_fmt=info:ofi/fmt:kev:mtx:journal&amp;rft.atitle=Automatic%20problem-specific%20hyperparameter%20optimization%20and%20model%20selection%20for%20supervised%20machine%20learning:%20Technical%20Report&amp;rft.date=2015&amp;rft.au=Berm%C3%BAdez-Chac%C3%B3n,%20R%C3%B3ger&amp;Gonnet,%20Gaston%20H.&amp;Smith,%20Kevin&amp;rft.genre=report&amp;rft.btitle=Automatic%20problem-specific%20hyperparameter%20optimization%20and%20model%20selection%20for%20supervised%20machine%20learning:%20Technical%20Report
 Search via SFX

Files in this item

Thumbnail

Publication type

Show simple item record