Scipediacontent: Scipediacontent moved page Draft Content 533326535 to Moore Olson 2016a

2021-01-25T10:20:19Z

Scipediacontent moved page Draft Content 533326535 to Moore Olson 2016a

Scipediacontent: Created page with " == Abstract == As data science continues to grow in popularity, there will be an increasing need to make data science tools more scalable, flexible, and accessible. In parti..."

2021-01-25T10:20:16Z

Created page with " == Abstract == As data science continues to grow in popularity, there will be an increasing need to make data science tools more scalable, flexible, and accessible. In parti..."

New page

== Abstract ==

As data science continues to grow in popularity, there will be an increasing need to make data science tools more scalable, flexible, and accessible. In particular, automated machine learning (AutoML) systems seek to automate the process of designing and optimizing machine learning pipelines. In this chapter, we present a genetic programming-based AutoML system called TPOT that optimizes a series of feature preprocessors and machine learning models with the goal of maximizing classification accuracy on a supervised classification problem. Further, we analyze a large database of pipelines that were previously used to solve various supervised classification problems and identify 100 short series of machine learning operations that appear the most frequently, which we call the building blocks of machine learning pipelines. We harness these building blocks to initialize TPOT with promising solutions, and find that this sensible initialization method significantly improves TPOT's performance on one benchmark at no cost of significantly degrading performance on the others. Thus, sensible initialization with machine learning pipeline building blocks shows promise for GP-based AutoML systems, and should be further refined in future work.

== Original document ==

The different versions of the original document can be found in:

* [http://arxiv.org/abs/1607.08878 http://arxiv.org/abs/1607.08878]

* [http://arxiv.org/pdf/1607.08878 http://arxiv.org/pdf/1607.08878]

* [http://link.springer.com/content/pdf/10.1007/978-3-319-97088-2_14 http://link.springer.com/content/pdf/10.1007/978-3-319-97088-2_14],
: [http://dx.doi.org/10.1007/978-3-319-97088-2_14 http://dx.doi.org/10.1007/978-3-319-97088-2_14] under the license http://www.springer.com/tdm

* [https://dblp.uni-trier.de/db/journals/corr/corr1607.html#OlsonM16 https://dblp.uni-trier.de/db/journals/corr/corr1607.html#OlsonM16],
: [https://arxiv.org/abs/1607.08878 https://arxiv.org/abs/1607.08878],
: [https://ui.adsabs.harvard.edu/abs/2016arXiv160708878O/abstract https://ui.adsabs.harvard.edu/abs/2016arXiv160708878O/abstract],
: [https://link.springer.com/chapter/10.1007/978-3-319-97088-2_14 https://link.springer.com/chapter/10.1007/978-3-319-97088-2_14],
: [https://academic.microsoft.com/#/detail/2962924528 https://academic.microsoft.com/#/detail/2962924528]

← Older revision	Revision as of 10:20, 25 January 2021
(No difference)

Moore Olson 2016a - Revision history

Scipediacontent: Scipediacontent moved page Draft Content 533326535 to Moore Olson 2016a

Scipediacontent: Created page with " == Abstract == As data science continues to grow in popularity, there will be an increasing need to make data science tools more scalable, flexible, and accessible. In parti..."