eBird: A Human / Computer Learning Network to Improve Biodiversity Conservation and Research

We call this a human/computer learning network, whose core is an active learning feedback loop between humans and machines that dramatically improves the quality of both and thereby continually improves the effectiveness of the network as a whole. In this article we explore how human/computer learning networks can leverage the contributions of human observers and process their contributed data with artificial intelligence algorithms leading to a computational power that far exceeds the sum of the individual parts. For example, projects such as Galaxy Zoo, eBird, and FoldIt demonstrate the power of engaging the public in the investigation of a variety of large-scale scientific problems. These and similar projects leverage emerging techniques that integrate the speed and scalability of mechanical computation, using advances in artificial intelligence (AI), with the real intelligence of human computation to solve computational problems that are beyond the scope of existing algorithms (Law and von Ahn 2011). Human computational systems use the innate abilities of humans to solve certain problems that computers cannot solve (Man-Ching, Ling-Jyh, and King 2009).