Human-in-the-loop machine learning: a state of the art
![Thumbnail](/dspace/bitstream/handle/2183/37615/MosqueiraRey_Eduardo_2023_Human_in_the_loop_machine_learning.pdf.jpg?sequence=6&isAllowed=y)
Use this link to cite
http://hdl.handle.net/2183/37615
Except where otherwise noted, this item's license is described as Attribution 4.0 International (CC BY)
Collections
- GI-LIDIA - Artigos [63]
Metadata
Show full item recordTitle
Human-in-the-loop machine learning: a state of the artAuthor(s)
Date
2023-04Citation
Mosqueira-Rey, E., Hernández-Pereira, E., Alonso-Ríos, D. et al. Human-in-the-loop machine learning: a state of the art. Artif Intell Rev 56, 3005–3054 (2023). https://doi.org/10.1007/s10462-022-10246-w
Abstract
[Abstract]: Researchers are defining new types of interactions between humans and machine learning algorithms generically called human-in-the-loop machine learning. Depending on who is in control of the learning process, we can identify: active learning, in which the system remains in control; interactive machine learning, in which there is a closer interaction between users and learning systems; and machine teaching, where human domain experts have control over the learning process. Aside from control, humans can also be involved in the learning process in other ways. In curriculum learning human domain experts try to impose some structure on the examples presented to improve the learning; in explainable AI the focus is on the ability of the model to explain to humans why a given solution was chosen. This collaboration between AI models and humans should not be limited only to the learning process; if we go further, we can see other terms that arise such as Usable and Useful AI. In this paper we review the state of the art of the techniques involved in the new forms of relationship between humans and ML algorithms. Our contribution is not merely listing the different approaches, but to provide definitions clarifying confusing, varied and sometimes contradictory terms; to elucidate and determine the boundaries between the different methods; and to correlate all the techniques searching for the connections and influences between them.
Keywords
Active learning
Curriculum learning
Explainable AI
Human-in-the-loop machine learning
Interactive machine learning
Machine teaching
Curriculum learning
Explainable AI
Human-in-the-loop machine learning
Interactive machine learning
Machine teaching
Editor version
Rights
Attribution 4.0 International (CC BY)
ISSN
0269-2821
Related items
Showing items related by title, author, creator and subject.
-
Enfoques de Aprendizaje en estudiantes de universidad : la escala bifactorial CEPE-U2F
Barca-Lozano, Alfonso; Peralbo, Manuel; Brenlla-Blanco, Juan-Carlos; Barca Enríquez, Eduardo (Universidade da Coruña, Servizo de Publicacións, 2019)[Resumen] Este trabajo tiene por finalidad la elaboración de la Escala abreviada de evaluación de enfoques de aprendizaje a partir de la Escala original de John Biggs (SPQ-Study Process Questionnaire) con una muestra de ... -
Deep Learning Language Models for Music Analysis and Generation
Quintillán Quintillán, Daniel (2022)[Abstract] In this project, we tackle the problem of predicting the next note in a monophonic musical piece. We choose a symbolic representation and extract it from digital sheet music. The problem is approached as four ... -
Comportamientos visuales sencillos en robots móviles Ranger mediante aprendizaje por refuerzo
García Cerqueiras, Aarón (2022)[Resumen] En este trabajo se desarrolla un sistema que permite generar, mediante aprendizaje por refuerzo, comportamientos basados en las imágenes capturadas por una cámara en un robot capaz de moverse por sí mismo. A ...