Filters








5,449 Hits in 4.7 sec

Preprocessor Selection for Machine Learning Pipelines [article]

Brandon Schoenfeld, Christophe Giraud-Carrier, Mason Poggemann, Jarom Christensen, Kevin Seppi
2018 arXiv   pre-print
In other words, practical solutions consist of pipelines of machine learning operators rather than single algorithms.  ...  Here, we conduct an extensive empirical study over a wide range of learning algorithms and preprocessors, and use metalearning to determine when one should make use of preprocessors in ML pipeline design  ...  Acknowledgments We gratefully acknowledge support from the Defense Advanced Research Projects Agency under award FA8750-17-2-0082.  ... 
arXiv:1810.09942v1 fatcat:cxwm76e57bdh7pzx6mmmyyuvwq

AL: autogenerating supervised learning programs

José P. Cambronero, Martin C. Rinard
2019 Proceedings of the ACM on Programming Languages (PACMPL)  
In contrast to existing automated machine learning tools, which typically implement a search over manually selected machine learning functions and classes, AL learns to identify the relevant classes in  ...  We present AL, a novel automated machine learning system that learns to generate new supervised learning pipelines from an existing corpus of supervised learning programs.  ...  A meta-learning approach to automatic kernel selection for support vector machines.  ... 
doi:10.1145/3360601 fatcat:ylpowzztxzc3bbzuv5kmaebehm

Evaluating Meta-Feature Selection for the Algorithm Recommendation Problem [article]

Geand Trindade Pereira, Moises Rocha dos Santos, Andre Carlos Ponce de Leon Ferreira de Carvalho
2021 arXiv   pre-print
The present study was focused on three criteria: predictive performance, dimensionality reduction, and pipeline runtime.  ...  In this context, the problem of Algorithm Recommendation (AR) is receiving a significant deal of attention recently.  ...  Introduction The machine learning popularity in automated systems is increasing daily [1] .  ... 
arXiv:2106.03954v2 fatcat:cvuopgyiafbgxkgolrhtchheoi

A Machine Learning Based Software Pipeline to Pick the Variable Ordering for Algorithms with Polynomial Inputs [chapter]

Dorian Florescu, Matthew England
2020 Lecture Notes in Computer Science  
We are interested in the application of Machine Learning (ML) technology to improve mathematical software.  ...  Hence in this paper we present a software pipeline to use sklearn to pick the variable ordering for an algorithm that acts on a polynomial system. The code described is freely available online.  ...  This work is funded by EPSRC Project EP/R019622/1: Embedding Machine Learning within Quantifier Elimination Procedures. We thank the anonymous referees for their comments.  ... 
doi:10.1007/978-3-030-52200-1_30 fatcat:mkrpckkoxnevpdiynqfwny6rhu

A machine learning based software pipeline to pick the variable ordering for algorithms with polynomial inputs [article]

Dorian Florescu, Matthew England
2020 arXiv   pre-print
We are interested in the application of Machine Learning (ML) technology to improve mathematical software.  ...  Hence in this paper we present a software pipeline to use sklearn to pick the variable ordering for an algorithm that acts on a polynomial system. The code described is freely available online.  ...  Acknowledgements This work is funded by EPSRC Project EP/R019622/1: Embedding Machine Learning within Quantifier Elimination Procedures. We thank the anonymous referees for their comments.  ... 
arXiv:2005.11251v1 fatcat:7xhxvkgkpfcz3mjjvr6uem7bmq

PHOTONAI – A Python API for Rapid Machine Learning Model Development [article]

Ramona Leenings, Nils Ralf Winter, Lucas Plagwitz, Vincent Holstein, Jan Ernsting, Jakob Steenweg, Julian Gebker, Kelvin Sarink, Daniel Emden, Dominik Grotegerd, Nils Opel, Benjamin Risse (+3 others)
2021 arXiv   pre-print
Its practical utility is demonstrated on an exemplary medical machine learning problem, achieving a state-of-the-art solution in few lines of code.  ...  A growing add-on ecosystem allows researchers to offer data modality specific algorithms to the community and enhance machine learning in the areas of the life sciences.  ...  Acknowledgments This work was supported by grants from the Interdisciplinary Center for Clinical Research (IZKF) of the medical faculty of Münster (grant MzH 3/020/20 to TH and grant Dan3/012/17 to UD)  ... 
arXiv:2002.05426v4 fatcat:c4chsgrwgnfknmu3akhqsj7txe

PHOTONAI—A Python API for rapid machine learning model development

Ramona Leenings, Nils Ralf Winter, Lucas Plagwitz, Vincent Holstein, Jan Ernsting, Kelvin Sarink, Lukas Fisch, Jakob Steenweg, Leon Kleine-Vennekate, Julian Gebker, Daniel Emden, Dominik Grotegerd (+6 others)
2021 PLoS ONE  
Its practical utility is demonstrated on an exemplary medical machine learning problem, achieving a state-of-the-art solution in few lines of code.  ...  A growing add-on ecosystem allows researchers to offer data modality specific algorithms to the community and enhance machine learning in the areas of the life sciences.  ...  It combines an automated supervised machine learning workflow with the concept of custom machine learning pipelines.  ... 
doi:10.1371/journal.pone.0254062 pmid:34288935 fatcat:temwqhamh5bopi4rmdvn2xbwwm

How can AI Automate End-to-End Data Science? [article]

Charu Aggarwal, Djallel Bouneffouf, Horst Samulowitz, Beat Buesser, Thanh Hoang, Udayan Khurana, Sijia Liu, Tejaswini Pedapati, Parikshit Ram, Ambrish Rawat, Martin Wistuba, Alexander Gray
2019 arXiv   pre-print
Then we provide several views on how AI could succeed in automating end-to-end AutoDS.  ...  Data science is labor-intensive and human experts are scarce but heavily involved in every aspect of it.  ...  A key part of data science is machine learning in which the system learns from data-driven examples in order to make predictions about examples in which some of the attributes are missing.  ... 
arXiv:1910.14436v1 fatcat:g7rjqv6mnvb2bbkfigys4lk5iy

MachSMT: A Machine Learning-based Algorithm Selector for SMT Solvers

Joseph Scott, Aina Niemetz, Mathias Preiner, Saeed Nejati, Vijay Ganesh
2021 Zenodo  
[20] , which won the Godel Prize in 2003. In ensemble learning, a set of learning algorithms (e.g., weak learners) are trained, and predictions are made diplomatically across the set.  ...  Algorithm selectors have been extensively used in many contexts, e.g., classifiers for machine learning [3] , combinatorics [36] , and other NP-hard optimization problems [56, 57] .  ... 
doi:10.5281/zenodo.4458698 fatcat:zgirqirgfbhfvahxpsbfik4o4i

AutoAIViz: Opening the Blackbox of Automated Artificial Intelligence with Conditional Parallel Coordinates [article]

Daniel Karl I. Weidele, Justin D. Weisz, Eno Oduor, Michael Muller, Josh Andres, Alexander Gray, Dakuo Wang
2020 arXiv   pre-print
Artificial Intelligence (AI) can now automate the algorithm selection, feature engineering, and hyperparameter tuning steps in a machine learning workflow.  ...  We find that the proposed system helps users to complete the data science tasks, and increases their understanding, toward the goal of increasing trust in the AutoAI system.  ...  -in-the-loop Data Science and Automated Machine Learning Many studies have focused on understanding the work practices of data scientists.  ... 
arXiv:1912.06723v2 fatcat:bwvd6gapo5ejllm42rwld7b65y

Automated adaptation strategies for stream learning

Rashid Bakirov, Damien Fay, Bogdan Gabrys
2021 Machine Learning  
AbstractAutomation of machine learning model development is increasingly becoming an established research area.  ...  In this paper we address this issue by proposing the use of flexible adaptive mechanism deployment for automated development of adaptation strategies.  ...  We also would like to thank Evonik Industries AG for the provided datasets. Part of the used Matlab code originates from Petr Kadlec and Ratko Grbić.  ... 
doi:10.1007/s10994-021-05992-x fatcat:bvsrrefomzemnhzteqp2d2obmi

Big Universe, Big Data: Machine Learning and Image Analysis for Astronomy

Jan Kremer, Kristoffer Stensbo-Smidt, Fabian Gieseke, Kim Steenstrup Pedersen, Christian Igel
2017 IEEE Intelligent Systems  
Thus, modern astronomy requires big data know-how, in particular it demands highly efficient machine learning and image analysis algorithms.  ...  The advent of wide-area digital cameras on large aperture telescopes has led to ever more ambitious surveys of the sky.  ...  This interpretability of predictions is typically not provided when using a machine learning approach.  ... 
doi:10.1109/mis.2017.40 fatcat:73zk6fysgrfmroqbwzage33tu4

Towards a Reference Software Architecture for Human-AI Teaming in Smart Manufacturing [article]

Philipp Haindl, Georg Buchgeher, Maqbool Khan, Bernhard Moser
2022 arXiv   pre-print
In the frame of the EU funded Teaming.AI project, we identified the monitoring of teaming aspects in human-AI collaboration, the runtime monitoring and validation of ethical policies, and the support for  ...  This allows for context-specific recommendations for actions in the manufacturing process for the optimization of product quality and the prevention of physical harm.  ...  ACKNOWLEDGEMENTS This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 957402.  ... 
arXiv:2201.04876v5 fatcat:3hxd3pqomzbi7a6zm54f47hnry

Infrastructure for Usable Machine Learning: The Stanford DAWN Project [article]

Peter Bailis, Kunle Olukotun, Christopher Re, Matei Zaharia
2017 arXiv   pre-print
In this document, we outline opportunities for infrastructure supporting usable, end-to-end machine learning applications in the context of the nascent DAWN (Data Analytics for What's Next) project at  ...  Despite incredible recent advances in machine learning, building machine learning applications remains prohibitively time-consuming and expensive for all but the best-trained, best-funded engineering organizations  ...  ii)) in an end-to-end validation of the DAWN project output.  ... 
arXiv:1705.07538v2 fatcat:hqtuldds4bdtpg6btl5sy3id7e

Efficient AutoML Pipeline Search with Matrix and Tensor Factorization [article]

Chengrun Yang, Jicong Fan, Ziyang Wu, Madeleine Udell
2020 arXiv   pre-print
In this work, we design a new AutoML system to address this challenge: an automated system to design a supervised learning pipeline.  ...  With new pipeline components comes a combinatorial explosion in the number of choices!  ...  Dunn for a script to parse UCI Machine Learning Repository datasets.  ... 
arXiv:2006.04216v1 fatcat:x5kjf2zy5zb3hnlgpjkixlt5hy
« Previous Showing results 1 — 15 out of 5,449 results