Title: Making machine learning useable by revealing internal states update - a transparent approach

Authors: Jianlong Zhou; M. Asif Khawaja; Zhidong Li; Jinjun Sun; Yang Wang; Fang Chen

Addresses: National ICT Australia (NICTA), Level 5, 13 Garden Street, Eveleigh, NSW 2015, Australia ' National ICT Australia (NICTA), Level 5, 13 Garden Street, Eveleigh, NSW 2015, Australia ' National ICT Australia (NICTA), Level 5, 13 Garden Street, Eveleigh, NSW 2015, Australia ' National ICT Australia (NICTA), Level 5, 13 Garden Street, Eveleigh, NSW 2015, Australia ' National ICT Australia (NICTA), Level 5, 13 Garden Street, Eveleigh, NSW 2015, Australia ' National ICT Australia (NICTA), Level 5, 13 Garden Street, Eveleigh, NSW 2015, Australia

Abstract: Machine learning (ML) techniques are often found difficult to apply effectively in practice because of their complexities. Therefore, making ML useable is emerging as one of active research fields recently. Furthermore, an ML algorithm is still a 'black-box'. This 'black-box' approach makes it difficult for users to understand complicated ML models. As a result, the user is uncertain about the usefulness of ML results and this affects the effectiveness of ML methods. This paper focuses on making a 'black-box' ML process transparent by presenting real-time internal status update of the ML process to users explicitly. A user study was performed to investigate the impact of revealing internal status update to users on the easiness of understanding data analysis process, meaningfulness of real-time status update, and convincingness of ML results. The study showed that revealing of the internal states of ML process can help improve easiness of understanding the data analysis process, make real-time status update more meaningful, and make ML results more convincing.

Keywords: machine learning; black box approach; transparency; internal status update; ease of understanding; data analysis; meaningfulness.

DOI: 10.1504/IJCSE.2016.080214

International Journal of Computational Science and Engineering, 2016 Vol.13 No.4, pp.378 - 389

Received: 10 Nov 2014
Accepted: 08 Jan 2015

Published online: 04 Nov 2016 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article