For one of my class projects, I’ve been reading a lot about interactive machine learning – an approach which Karl Sims describes as allowing “the user and computer to interactively work together in a new way to produce results that neither could easily produce alone.”
In someways, this approach is intuitive. Michael Muller, for example, argues that any work with technology has an inherently social dimension. “Must we always analyze the impact of technology on people,” he asks, “or is there just as strong an impact of people on technology?” From this perspective, any machine learning approach which doesn’t account for both the user and the algorithm is incomplete.
Jerry Fails and Dan Olsen fully embrace this approach, proposing a paradigm shift in the fundamental way researchers approach machine learning tasks. While classic machine learning models “require the user to choose features and wait an extended amount of time for the algorithm to train,” Fails and Olsen propose an interactive machine learning approach which feeds a large number of features into a classifier, with human judgement continually correcting and refining the results. They find this approach removes the need to pre-select features, reduces the burden of technical knowledge on the user, and significantly speeds up training.