AutoML: Streamlining and Automating the Machine Learning Pipeline
Keywords:
Automated Machine Learning, Neural architecture search, Reinforcement learning, Machine learningAbstract
The goal of the developing discipline of "Automated Machine Learning," or "AutoML," is to automate the process of creating machine learning models. By automating as much of the repetitive, unproductive labor that arises when machine learning is used, autoML was developed to boost productivity and efficiency. The development of machine learning models is made easier by the revolutionary technique known as Automated Machine Learning (AutoML). An overview of current developments in automated machine learning pipelines and AutoML approaches is given in this study. To sum up, automated machine learning pipelines have a great deal of potential to advance the field of machine learning, spur innovation, and influence the direction of artificial intelligence. Through the use of AutoML and multidisciplinary cooperation, we can solve intricate problems, open up new avenues, and build a future where intelligent automation enables people and businesses to prosper in the digital era.
References
[1] I. Salehin et al., "AutoML : A systematic review on automated machine learning with neural architecture search," J. Inf. Intell., vol. 2, no. 1, pp. 52-81, 2024,
https://doi.org/10.1016/j.jiixd.2023.10.002
[2] R. Dharani et al., "AutoML and Automated Machine Learning Pipelines Dharani," no. 5, pp. 9661-9668, 2024.
[3] M. Baratchi et al., Automated machine learning : past , present and future, vol. 57, no. 5. Springer Netherlands, 2024.
https://doi.org/10.1007/s10462-024-10726-1
[4] A. Moharil, J. Vanschoren, P. Singh, and D. Tamburri, Towards efficient AutoML: a pipeline synthesis approach leveraging pre‑trained transformers for multimodal data Ambarish, vol. 113, no. 9. Springer US, 2024.
https://doi.org/10.1007/s10994-024-06568-1
[5] H. Kaur, "AutoML : Streamlining the Machine Learning Pipeline for Efficient Model Development," vol. 4, pp. 1-4, 2023.
[6] O. O. Bifarin and F. M. Fernández, "Automated machine learning and explainable AI ( AutoML-XAI ) for metabolomics : improving cancer diagnostics .," no. Ml, 2023.
https://doi.org/10.1101/2023.10.26.564244
[7] G. Baudart, P. Ram, M. Hirzel, K. Kate, J. Tsay, and A. Shinnar, "Pipeline Combinators for Gradual AutoML," no. NeurIPS, 2021.
[8] D. Kißkalt, A. Mayr, B. Lutz, A. Rögele, and J. Franke, "Streamlining the development of data-driven industrial applications by automated machine learning," Procedia CIRP, vol. 93, no. March, pp. 401-406, 2020,
