TradeBriefs Editorial

From the Editor's Desk

A radical new technique lets AI learn with practically no data

"Less than one"-shot learning can teach a model to identify more objects than the number of examples it is trained on.

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.

Now a new paper from the University of Waterloo in Ontario suggests that AI models should also be able to do this - 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. That could be a big deal for a field that has grown increasingly expensive and inaccessible as the data sets used become ever larger.

Continued here

TradeBriefs: What's important, not just what's popular!

Advertisers of the day

Emeritus: PG Diploma in Innovation & Design Thinking online program | Accepting applications

Emeritus : PG Diploma in Digital Marketing Strategies in collaboration with Columbia Business School Executive Education | Apply

Our advertisers help fund the daily operations of TradeBriefs. We request you to accept our promotional emails.

You are here: Home Opinion A radical new technique lets AI learn with practically no data