AI is Learning With Almost No Data

A radical new technique means AI is learning with practically no data. A model can learn to identify more objects than the number of examples it is trained on.

A new paper from the University of Waterloo in Ontario suggests that AI models should be able to put together an image from other images. It is a process the researchers call “less than one”-shot, or LO-shot, learning. In other words, an AI model should be able to accurately recognize more objects than the number of examples it was trained on – AI is learning better. That could be a big deal for a field that has grown increasingly expensive and inaccessible as the data sets used become ever larger.