Visual Analytics to Build a Machine Learning Model

Visual Analytics to Build a Machine Learning Model

Iurii V. Krak (Glushkov Cybernetics Institute, Taras Shevchenko National University of Kyiv, Ukraine), Olexander V. Barmak (National University of Khmelnytskyi, Ukraine) and Eduard Manziuk (National University of Khmelnytskyi, Ukraine)
DOI: 10.4018/978-1-7998-3970-5.ch015


One of the most interesting and promising areas of development of machine learning is the active involvement of a human in the process of building a model. However, there are problems with the effective integration of humans into a workflow. It is necessary to develop techniques and information technologies that would allow the effective use of human intellectual capabilities, thereby expanding the machine learning tools. This work considers the use of visual analytics with the goal of building a machine learning model by a human and the technique of transferring this model to the machine level. This made it possible to expand the capabilities of machine learning through the active and productive use of human intellectual abilities.
Chapter Preview

Information Visualization

The field of information visualization has arisen as a result of studies of human-computer interaction, computer science, graphics, design, psychology and business methods. It is increasingly being used as the most important component in scientific research, digital libraries, data mining, financial data analysis, market research, industrial control. Visualization of information implies that visual representations and methods of interaction take advantage of the ability of the human eye to transmit information to the brain so that users can see, learn and understand a large amount of information at a time. Information visualization is aimed at creating approaches to the transfer of abstract information into intuitive images (Thomas & Cook, 2005).

Complete Chapter List

Search this Book: