2018
DOI: 10.1007/s10489-018-1361-5
|View full text |Cite
|
Sign up to set email alerts
|

Interactive machine learning: experimental evidence for the human in the algorithmic loop

Abstract: Recent advances in automatic machine learning (aML) allow solving problems without any human intervention. However, sometimes a human-in-the-loop can be beneficial in solving computationally hard problems. In this paper we provide new experimental insights on how we can improve computational intelligence by complementing it with human intelligence in an interactive machine learning approach (iML). For this purpose, we used the Ant Colony Optimization (ACO) framework, because this fosters multi-agent approaches… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
83
0
2

Year Published

2019
2019
2022
2022

Publication Types

Select...
8
1

Relationship

4
5

Authors

Journals

citations
Cited by 185 publications
(93 citation statements)
references
References 70 publications
0
83
0
2
Order By: Relevance
“…Ante‐hoc systems are interpretable by design towards glass‐box approaches (Holzinger et al, , ); typical examples include linear regression, decision trees and fuzzy inference systems. The latter have a long tradition and can be designed from expert knowledge or from data and provides—from the viewpoint of Human‐AI interaction—a good framework for the interaction between human expert knowledge and hidden knowledge in the data (Guillaume, ).…”
Section: General Approaches Of Explainable Ai Modelsmentioning
confidence: 99%
“…Ante‐hoc systems are interpretable by design towards glass‐box approaches (Holzinger et al, , ); typical examples include linear regression, decision trees and fuzzy inference systems. The latter have a long tradition and can be designed from expert knowledge or from data and provides—from the viewpoint of Human‐AI interaction—a good framework for the interaction between human expert knowledge and hidden knowledge in the data (Guillaume, ).…”
Section: General Approaches Of Explainable Ai Modelsmentioning
confidence: 99%
“…Die Nachvollziehbarkeit, Interpretation und Verstehbarkeit von Ergebnissen maschineller Lernalgorithmen und Möglichkeiten die Qualität von KI zu evaluieren rücken damit in das Zentrum des Interesses von Wissenschaft und Wirtschaft. Durch die schwächen so-genannter "Black-Box" Algorithmen sowie sozialer und ethischer Verantwortlichkeit ist man, zumindest in Domänen wie der Medizin, wieder stärker motiviert an einer Verbindung von menschlicher Intelligenz und maschineller Intelligenz ("augmenting human intelligence with artificial intelligence") zu arbeiten und die Stärken von KI und menschlicher Intelligenz zu verbinden (Holzinger 2016a;Holzinger et al 2019b).…”
Section: Einführung Und Motivationunclassified
“…by application of interactive ML (iML) methods [92,93], which also enable to explain why a machine decision has been reached [94,95]. Technically, this will be done by applying algorithms which enable an integration of a human into the algorithmic loop, who can then provide his/her expertise to find the underlying explanatory factors [96].…”
Section: The Role Of Computer Science Ai and ML In Integrating Virtumentioning
confidence: 99%