eBird is a citizen-science project that takes advantage of the human observational capacity to identify birds to species, and uses these observations to accurately represent patterns of bird occurrences across broad spatial and temporal extents. eBird employs a global network of observers who have submitted more than 100 million observations of birds, making it one of the largest biodiversity data sources in existence. eBird employs artificial intelligence techniques such as machine learning to improve data quality by taking advantage of the synergies between human
computation and digital computation. We call this a Human/Computer Learning Network, whose core is an active learning feedback loop between humans and computers that dramatically improves the quality of both, and thereby
continually improves the effectiveness of the network as a whole. In this talk, I will describe how using these techniques eBird has become an effective "data-driven" tool to solve ecological and conservation problems
across multiple spatial and temporal scales.