Abstract
Today, the number of applications and tasks that use AI is rapidly growing. It is used where the task is too difficult to solve for a human or requires a lot of manual work. While AI algorithms are black boxes most of the time, the success of an AI model highly correlates with the quality of the labeled data. 60% to 80% of the time spend training an AI model is data preparation. Of course, data preparation includes labeling. Moreover, a lot of data is needed to train and improve AI models. If time is crucial or the amount of data is limited, other solutions have to be used to create a satisfactory model. Often, an AI expert is needed to create such models. Therefore, we developed the Zauberzeug Learning Loop, a no-code web platform that uses Active Learning to reduce the amount of data needed. The system is currently tested in different projects and can be used in various fields of AI use cases like agriculture.
Similar content being viewed by others
References
Artificial intelligence in agriculture market. https://www.emergenresearch.com/industry-report/artificial-intelligence-in-agriculture-market (2022). Accessed: 2022-09-14
Butte S, Vakanski A, Duellman K, Wang H, Mirkouei A (2021) Agron J 113(5):3991
Gao J, French AP, Pound MP, He Y, Pridmore TP, Pieters JG (2020) Plant Methods 16(1):29. https://doi.org/10.1186/s13007-020-00570-z
Sager C, Janiesch C, Zschech P (2021) A survey of image labelling for computer vision applications. J Bus Anal 4(2):91. https://doi.org/10.1080/2573234X.2021.1908861
Data engineering, preparation, and labeling for ai 2020. https://www.cognilytica.com/document/data-preparation-labeling-for-ai-2020/ (2020). Accessed: 2022-09-14
Szeliski R (2011) Computer vision algorithms and applications. Springer, London; New York
The no-code computer vision platform. https://viso.ai. Accessed: 2022-10-04
Give your software the sense of sight. https://roboflow.com/. Accessed: 2022-10-04
Unlock your data. unleash your ai. https://labelbox.com/. Accessed: 2023-05-16
Unified os/platform for computer vision. https://supervisely.com/. Accessed: 2023-05-16
Monarch RM (2021) Human-in-the-Loop Machine Learning: Active learning and annotation for human-centered AI (Simon and Schuster)
Sugimori Y, Kusunoki K, Cho F, Uchikawa S (1977) Toyota production system and Kanban system: materialization of just-in-time and respect for human systems. Int J Prod Res 15(6):553. https://doi.org/10.1080/00207547708943149
Zhuang F, Qi Z, Duan K, Xi D, Zhu Y, Zhu H, Xiong H, He Q (2019) CoRR abs/1911.02685. http://arxiv.org/abs/1911.02685
Nowakowski A, Mrziglod J, Spiller D, Bonifacio R, Ferrari I, Mathieu PP, Garcia-Herranz M, Kim DH (2021) Int J Appl Earth Obs Geoinform 98:102313. 10.1016/j.jag.2021.102313
Angular: The modern web developer’s platform. https://angular.io/. Accessed: 2022-11-30
Ramirez, S. Fastapi. https://fastapi.tiangolo.com/. Accessed: 2022-11-29
Postgresql: The world’s most advanced open source relational database. https://www.postgresql.org/. Accessed: 2022-11-30
Rauch G (2013) Socket. io: the cross-browser websocket for realtime apps. https://socket.io . Accessed: 2022-09-12
This python library helps you to write your own detection nodes, training nodes and converter nodes for the zauberzeug learning loop. https://github.com/zauberzeug/learning_loop_node. Accessed: 2023-05-17
zuckerrübe. https://region40.de/hf1-projekt-zuckerruebe/. Accessed: 2022-11-30
Zauberzeug robot brain. https://zauberzeug.com/robot-brain.html. Accessed: 2022-09-12
Innovation award eurotier 2022. https://www.eurotier.com/de/awards/innovation-award/gewinner-2022. Accessed: 2022-10-31
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Glahe, P., Trappe, R. Zauberzeug Learning Loop. Künstl Intell (2024). https://doi.org/10.1007/s13218-023-00816-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13218-023-00816-7