Filters








23 Hits in 8.9 sec

ML-Plan: Automated machine learning via hierarchical planning

Felix Mohr, Marcel Wever, Eyke Hüllermeier
2018 Machine Learning  
Automated machine learning (AutoML) seeks to automatically select, compose, and parametrize machine learning algorithms, so as to achieve optimal performance on a given task (dataset).  ...  In this paper, we present ML-Plan, a new approach to AutoML based on hierarchical planning.  ...  ML-Plan ML-Plan reduces AutoML to a graph search problem via HTN planning.  ... 
doi:10.1007/s10994-018-5735-z fatcat:mxubyy32bvftzd4i4dsrrnv63a

Automated Machine Learning Service Composition [article]

Felix Mohr, Marcel Wever, Eyke Hüllermeier
2018 arXiv   pre-print
This paper presents \tool, an algorithm for automated service composition applied to the area of machine learning.  ...  Automated service composition as the process of creating new software in an automated fashion has been studied in many different ways over the last decade.  ...  Case Study: Machine Learning Pipelines In our case study, we consider the domain of automated machine learning (Auto-ML).  ... 
arXiv:1809.00486v1 fatcat:europ35yvfhwbfj6ewl2pmdohq

Domain Adaptation of Automated Treatment Planning from Computed Tomography to Magnetic Resonance [article]

Aly Khalifa, Jeff Winter, Inmaculada Navarro, Chris McIntosh, Thomas G. Purdie
2022 arXiv   pre-print
Objective: Machine learning (ML) based radiation treatment (RT) planning addresses the iterative and time-consuming nature of conventional inverse planning.  ...  Significance: We were able to create highly acceptable MR based treatment plans using a CT-trained ML model for treatment planning, although clinically significant dose deviations from the CT based plans  ...  Introduction Machine learning (ML) has the potential to relieve the iterative and time-consuming nature of conventional inverse planning in radiation therapy (RT) by offering increased automation and decision  ... 
arXiv:2203.03576v1 fatcat:6trzberbijbppnmdhkm2ag2pg4

AutoML for Multi-Label Classification: Overview and Empirical Evaluation

Marcel Wever, Alexander Tornede, Felix Mohr, Eyke Hullermeier
2021 IEEE Transactions on Pattern Analysis and Machine Intelligence  
Automated machine learning (AutoML) supports the algorithmic construction and data-specific customization of machine learning pipelines, including the selection, combination, and parametrization of machine  ...  learning algorithms as main constituents.  ...  AUTOMATED MACHINE LEARNING D ESPITE the short history of automated machine learning (AutoML), a diverse array of methods has been proposed to tackle the problem of so-called combined algorithm selection  ... 
doi:10.1109/tpami.2021.3051276 fatcat:4p3hvjf26ff4pozl4x626juqja

Searching for Machine Learning Pipelines Using a Context-Free Grammar

Radu Marinescu, Akihiro Kishimoto, Parikshit Ram, Ambrish Rawat, Martin Wistuba, Paulito P. Palmes, Adi Botea
2021 AAAI Conference on Artificial Intelligence  
AutoML automatically selects, composes and parameterizes machine learning algorithms into a workflow or pipeline of operations that aims at maximizing performance on a given dataset.  ...  Introduction Automated Machine Learning (or AutoML for short) seeks to automatically compose and parameterize machine learning algorithms to maximize a given metric such as predictive accuracy on a given  ...  ML-Plan (Mohr, Wever, and Hullermeier 2018 ) is a recent system that assumes a fixed linear structure of the pipelines and uses a form of AI planning called hierarchical task networks (HTN) to optimize  ... 
dblp:conf/aaai/0002KRRWPB21 fatcat:4mftppf5zvdrfc434b3knbb75i

Incremental Search Space Construction for Machine Learning Pipeline Synthesis [article]

Marc-André Zöller, Tien-Dung Nguyen, Marco F. Huber
2021 arXiv   pre-print
Automated machine learning (AutoML) aims for constructing machine learning (ML) pipelines automatically.  ...  ML-Plan [15] traverses a hierarchical task network with a MCTS to perform PSO. By design, the structure is determined first followed by the HPO.  ...  To prevent a leaking of information via meta-learning in dswizard, we construct an individual meta-learning base for each data set excluding the data set under evaluation.  ... 
arXiv:2101.10951v1 fatcat:2jtf7ljkgfcfhojqzwmrnrplty

VolcanoML: Speeding up End-to-End AutoML via Scalable Search Space Decomposition [article]

Yang Li, Yu Shen, Wentao Zhang, Jiawei Jiang, Bolin Ding, Yaliang Li, Jingren Zhou, Zhi Yang, Wentao Wu, Ce Zhang, Bin Cui
2021 arXiv   pre-print
VolcanoML further supports a Volcano-style execution model - akin to the one supported by modern database systems - to execute the plan constructed.  ...  VolcanoML introduces and implements basic building blocks that decompose a large search space into smaller ones, and allows users to utilize these building blocks to compose an execution plan for the AutoML  ...  ., H2O [41] , Microsoft's Azure Machine Learning [2] , Google's Prediction API [20] , Amazon Machine Learning [49] and IBM's Watson Studio AutoAI [28] . Automating Individual Components.  ... 
arXiv:2107.08861v1 fatcat:twfsk2u54rhejpc65fs6j35pwi

Solving Constrained CASH Problems with ADMM [article]

Parikshit Ram, Sijia Liu, Deepak Vijaykeerthi, Dakuo Wang, Djallel Bouneffouf, Greg Bramble, Horst Samulowitz, Alexander G. Gray
2020 arXiv   pre-print
The CASH problem has been widely studied in the context of automated configurations of machine learning (ML) pipelines and various solvers and toolkits are available.  ...  ML-Plan (Mohr et al., 2018) uses hierarchical task networks (HTN) planning for algorithm selection and randomized search for HPO, while MOSAIC (Rakotoarison et al., 2019) utilizes Monte-Carlo Tree  ...  Distributed optimiza- tion and statistical learning via the alternating direction method of multipliers. Foundations and Trends R in Machine Learning, 3(1):1-122, 2011.  ... 
arXiv:2006.09635v2 fatcat:ldiqvg57bjah7lvu56rbz5u5j4

Benchmark and Survey of Automated Machine Learning Frameworks [article]

Marc-André Zöller, Marco F. Huber
2021 arXiv   pre-print
Automated machine learning (AutoML) aims to reduce the demand for data scientists by enabling domain experts to build machine learning applications automatically without extensive knowledge of statistics  ...  and machine learning.  ...  Hierarchical task networks (HTNs) (Ghallab et al., 2004 ) are a method from automated planning that recursively partition a complex problem into easier subproblems.  ... 
arXiv:1904.12054v5 fatcat:3gbpofwnl5a3zduqr5vportaly

AutonoML: Towards an Integrated Framework for Autonomous Machine Learning [article]

David Jacob Kedziora and Katarzyna Musial and Bogdan Gabrys
2022 arXiv   pre-print
Over the last decade, the long-running endeavour to automate high-level processes in machine learning (ML) has risen to mainstream prominence, stimulated by advances in optimisation techniques and their  ...  In doing so, we survey developments in the following research areas: hyperparameter optimisation, multi-component models, neural architecture search, automated feature engineering, meta-learning, multi-level  ...  systems like ML-Plan [267, 268] .  ... 
arXiv:2012.12600v2 fatcat:6rj4ubhcjncvddztjs7tql3itq

Integration of Novel Sensors and Machine Learning for Predictive Maintenance in Medium Voltage Switchgear to Enable the Energy and Mobility Revolutions

Martin W. Hoffmann, Stephan Wildermuth, Ralf Gitzel, Aydin Boyaci, Jörg Gebhardt, Holger Kaul, Ido Amihai, Bodo Forg, Michael Suriyah, Thomas Leibfried, Volker Stich, Jan Hicking (+5 others)
2020 Sensors  
Furthermore, we present an approach to develop a predictive maintenance system based on novel sensors and machine learning.  ...  Combined with machine learning algorithms, the demands put on the distribution grid by the energy and mobility revolutions can be handled.  ...  Accordingly, the field of automated machine learning (AutoML) is rapidly growing as it promises to automate this task partially.  ... 
doi:10.3390/s20072099 pmid:32276442 fatcat:e53wo324c5btxjudbv2t3pofty

AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data [article]

Nick Erickson, Jonas Mueller, Alexander Shirkov, Hang Zhang, Pedro Larroy, Mu Li, Alexander Smola
2020 arXiv   pre-print
We introduce AutoGluon-Tabular, an open-source AutoML framework that requires only a single line of Python to train highly accurate machine learning models on an unprocessed tabular dataset such as a CSV  ...  In Workshop on Automatic Machine Learning, pp. 58-65, 2016. Mohr, F., Wever, M., and Hüllermeier, E. ML-Plan: Auto- mated machine learning via hierarchical planning.  ...  In Automated Machine Learning, Springer series on Challenges in Machine Learning, pp. 177-219. Springer, 2019. He, X., Zhao, K., and Chu, X.  ... 
arXiv:2003.06505v1 fatcat:cfigwvy23nghjab4s5qeymsble

Automated Machine Learning for Healthcare and Clinical Notes Analysis

Akram Mustafa, Mostafa Rahimi Azghadi
2021 Computers  
To accelerate embedding ML in more applications and incorporating it in real-world scenarios, automated machine learning (AutoML) is emerging.  ...  Machine learning (ML) has been slowly entering every aspect of our lives and its positive impact has been astonishing.  ...  Medication extraction [74] Automated ICD coding [85] Deep transfer learning for ICD coding [131] ICD coding via deep learning [132] Medical codes explainable prediction [23] ML models for clinical  ... 
doi:10.3390/computers10020024 fatcat:sojvfgq255f3zeccsunzwu4ve4

Benchmark and Survey of Automated Machine Learning Frameworks

Marc-André Zöller, Marco F. Huber
2021 The Journal of Artificial Intelligence Research  
Automated machine learning (AutoML) aims to reduce the demand for data scientists by enabling domain experts to build machine learning applications automatically without extensive knowledge of statistics  ...  and machine learning.  ...  Hierarchical task networks (HTNs) (Ghallab et al., 2004 ) are a method from automated planning that recursively partition a complex problem into easier subproblems.  ... 
doi:10.1613/jair.1.11854 fatcat:whi5mdcidrfffmid6mabprzug4

VolcanoML: speeding up end-to-end AutoML via scalable search space decomposition

Yang Li, Yu Shen, Wentao Zhang, Ce Zhang, Bin Cui
2022 The VLDB journal  
VolcanoML further supports a Volcano-style execution model -- akin to the one supported by modern database systems -- to execute the plan constructed.  ...  VolcanoML introduces and implements basic building blocks that decompose a large search space into smaller ones, and allows users to utilize these building blocks to compose an execution plan for the AutoML  ...  TPOT [69] and ML-Plan [64] use genetic algorithms and hierarchical task networks planning, respectively, to optimize over the pipeline space, and require discretization of the hyper-parameter space  ... 
doi:10.1007/s00778-022-00752-2 fatcat:fx4zyzu3czfehh2fvdxwkm6m4y
« Previous Showing results 1 — 15 out of 23 results