Summary: “Less than one”-shot learning can teach a model to identify more objects than the number of examples it is trained on.
Original author and publication date: Karen Hao – October 16, 2020
Futurizonte Editor’s Note: I must say I have a hard time understanding how AI can learn with “practically no data”. What is AI learning is no data is involved? Should we redefine “learning”?
From the article:
Machine learning typically requires tons of examples. To get an AI model to recognize a horse, you need to show it thousands of images of horses. This is what makes the technology computationally expensive—and very different from human learning. A child often needs to see just a few examples of an object, or even only one, before being able to recognize it for life.
In fact, children sometimes don’t need any examples to identify something. Shown photos of a horse and a rhino, and told a unicorn is something in between, they can recognize the mythical creature in a picture book the first time they see it.
How “less than one”-shot learning works
The researchers first demonstrated this idea while experimenting with the popular computer-vision data set known as MNIST. MNIST, which contains 60,000 training images of handwritten digits from 0 to 9, is often used to test out new ideas in the field.
In a previous paper, MIT researchers had introduced a technique to “distill” giant data sets into tiny ones, and as a proof of concept, they had compressed MNIST down to only 10 images. The images weren’t selected from the original data set but carefully engineered and optimized to contain an equivalent amount of information to the full set. As a result, when trained exclusively on the 10 images, an AI model could achieve nearly the same accuracy as one trained on all MNIST’s images.