AI Bibliography

WIKINDX Resources  

Chatzimparmpas, A., Martins, R. M., Jusufi, I., Kucher, K., Rossi, F., & Kerren, A. 2020, The state of the art in enhancing trust in machine learning models with the use of visualizations. Paper presented at Computer Graphics Forum. 
Resource type: Proceedings Article
BibTeX citation key: Chatzimparmpas2020
View all bibliographic details
Categories: Artificial Intelligence, Cognitive Science, Computer Science, Data Sciences, Decision Theory, Engineering, General, Mathematics, Medical science
Subcategories: Analytics, Big data, Decision making, Human decisionmaking, Human factors engineering, Informatics, Machine learning, Psychology of human-AI interaction
Creators: Chatzimparmpas, Jusufi, Kerren, Kucher, Martins, Rossi
Publisher: Wiley Online Library
Collection: Computer Graphics Forum
Attachments  
Abstract
Machine learning (ML) models are nowadays used in complex applications in various domains, such as medicine, bioinformat-ics, and other sciences. Due to their black box nature, however, it may sometimes be hard to understand and trust the resultsthey provide. This has increased the demand for reliable visualization tools related to enhancing trust in ML models, which hasbecome a prominent topic of research in the visualization community over the past decades. To provide an overview and presentthe frontiers of current research on the topic, we present a State-of-the-Art Report (STAR) on enhancing trust in ML modelswith the use of interactive visualization. We define and describe the background of the topic, introduce a categorization forvisualization techniques that aim to accomplish this goal, and discuss insights and opportunities for future research directions.Among our contributions is a categorization of trust against different facets of interactive ML, expanded and improved fromprevious research. Our results are investigated from different analytical perspectives: (a) providing a statistical overview, (b)summarizing key findings, (c) performing topic analyses, and (d) exploring the data sets used in the individual papers, all withthe support of an interactive web-based survey browser. We intend this survey to be beneficial for visualization researcherswhose interests involve making ML models more trustworthy, as well as researchers and practitioners from other disciplinesin their search for effective visualization techniques suitable for solving their tasks with confidence and conveying meaning totheir data.
  
WIKINDX 6.7.0 | Total resources: 1621 | Username: -- | Bibliography: WIKINDX Master Bibliography | Style: American Psychological Association (APA)