(Copyright: Sarella/Depositphotos)
Walter Lasecki, assistant professor in the College of Engineering and in the School of Information, has co-authored a paper introducing the “look-ahead approach,” a hybrid intelligence workflow that enables instantaneous crowdsourcing systems that can return crowd responses within milliseconds.
According to the published paper, “Bolt: Instantaneous Crowdsourcing via Just-in-Time Training:”
…real-time crowdsourcing has made it possible to solve problems that are beyond the scope of AI within a matter of seconds, not hours or days using traditional crowdsourcing techniques. While this has led to an increase in the potential application domains of crowdsourcing and human computation, problems that require machine-level speeds—on the order of milliseconds, not seconds—have remained out of reach because of the fundamental bounds of human perception.
But Lasecki says the research demonstrates it is possible to exceed these bounds by combining human and machine intelligence—the look-ahead approach. Through a series of crowd worker experiments, the research shows that this new approach can outperform the fastest individual worker “by approximately two orders of magnitude. Our work opens new avenues for hybrid intelligence systems that are as smart as people, but also far faster than humanly possible.”
The paper was accepted for publication and presentation at the 2018 CHI conference, held in April in Montreal.
