Human-in-the-loop: Explainable or accurate artificial intelligence by exploiting human bias?

Laura Valtonen, Saku J. Mäkinen

Tutkimustuotos: KonferenssiartikkeliScientificvertaisarvioitu

Abstrakti

Artificial intelligence (AI) is a major contributor in industry 4.0 and there exists a strong push for AI adoption across fields for both research and practice. However, AI has quite well elaborated risks for both business and general society. Hence, paying attention to avoiding hurried adoption of counter-productive practices is important. For both managerial and general social issues, the same solution is sometimes proposed: human-in-the-loop (HITL). However, HITL literature is contradictory: HITL is proposed to promote fairness, accountability, and transparency of AI, which are sometimes assumed to come at the cost of AI accuracy. Yet, HITL is also considered a way to improve accuracy. To make sense of the convoluted literature, we begin to explore qualitatively how explainability is constructed in a HITL process, and how method accuracy is affected as its function. To do this, we study qualitatively and quantitatively a multi-class classification task with multiple machine learning algorithms. We find that HITL can increase both accuracy and explainability, but not without deliberate effort to do so. The effort required to achieve both increased accuracy and explainability, requires an iterative HITL in which accuracy improvements are not continuous, but disrupted by unique and varying human biases shedding additional perspectives on the task at hand.

AlkuperäiskieliEnglanti
Otsikko2022 IEEE 28th International Conference on Engineering, Technology and Innovation, ICE/ITMC 2022 and 31st International Association for Management of Technology, IAMOT 2022 Joint Conference - Proceedings
KustantajaIEEE
ISBN (elektroninen)978-1-6654-8817-4
DOI - pysyväislinkit
TilaJulkaistu - 2022
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE International Conference on Engineering, Technology and Innovation and International Association for Management of Technology Joint Conference - Nancy, Ranska
Kesto: 19 kesäk. 202223 kesäk. 2022

Conference

ConferenceIEEE International Conference on Engineering, Technology and Innovation and International Association for Management of Technology Joint Conference
Maa/AlueRanska
KaupunkiNancy
Ajanjakso19/06/2223/06/22

Julkaisufoorumi-taso

  • Jufo-taso 1

!!ASJC Scopus subject areas

  • Management of Technology and Innovation
  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Information Systems and Management
  • Electrical and Electronic Engineering

Sormenjälki

Sukella tutkimusaiheisiin 'Human-in-the-loop: Explainable or accurate artificial intelligence by exploiting human bias?'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä