The everyday consumer is inundated with applications powered by machine learning. But in an ordinary day, do we encounter situations and choices which could also benefit from machine learning for which there is no specific tool invented yet? We describe scenarios where people without
any machine learning background could find it useful to define their own solution which uses machine learning. Although machine learning is becoming ubiquitous, the average person is unaware of the steps involved. This abstraction makes sense, in many situations, such as traffic predictions,
it is not necessary for the driver to know what machine learning algorithm is running. However, we consider examples where knowing how to incorporate machine learning into a problem would assist in decision making. We propose a workflow with operations leading to a final application. There
are several challenges here, namely, the average consumer is not expected to have a mathematical background, nor is expected to acquire any additional background. To achieve this new utility, we use a visual analytic pipeline which integrates machine learning and the person. We use the IEEE
VAST 2018 Challenge as a case study in which the user steps through the workflow. Finally, we envision the resulting application.
No References for this article.
No Supplementary Data.
No Article Media
Document Type: Research Article
Publication date: January 13, 2019
This article was made available online on January 13, 2019 as a Fast Track article with title: "Visual analytic process to familiarize the average person with ways to apply machine learning".
More about this publication?
For more than 30 years, the Electronic Imaging Symposium has been serving those in the broad community - from academia and industry - who work on imaging science and digital technologies. The breadth of the Symposium covers the entire imaging science ecosystem, from capture (sensors, camera) through image processing (image quality, color and appearance) to how we and our surrogate machines see and interpret images. Applications covered include augmented reality, autonomous vehicles, machine vision, data analysis, digital and mobile photography, security, virtual reality, and human vision. IS&T began sole sponsorship of the meeting in 2016. All papers presented at EIs 20+ conferences are open access.
Please note: For purposes of its Digital Library content, IS&T defines Open Access as papers that will be downloadable in their entirety for free in perpetuity. Copyright restrictions on papers vary; see individual paper for details.