'Ex Machina', here we come: A new algorithm helps computers learn the way we do

In a 'visual Turing test,' human judges couldn't tell them apart

Machine learning is all about getting computers to "understand" new concepts, but it's still a pretty inefficient process, often requiring hundreds of examples for training. That may soon change, however, thanks to new research published on Friday.

Aiming to shorten the learning process and make it more like the way humans acquire and apply new knowledge based on just a few examples, a team of researchers has developed what they call a Bayesian Program Learning framework and then used it to teach computers to identify and reproduce handwritten characters based on just a single example.

Whereas standard pattern-recognition algorithms represent concepts as configurations of pixels or collections of features, the BPL approach learns by “explaining” the data provided to the algorithm -- in this case, the sample character. Concepts are represented as probabilistic computer programs and the algorithm essentially programs itself by constructing code to produce the letter it sees. It can also capture variations in the way different people draw a given letter.

The model also “learns to learn” by using knowledge from previous concepts to speed learning on new ones, so it can use knowledge of the Latin alphabet to learn letters in the Greek alphabet more quickly, for example.

Most compelling of all is that the algorithm allowed computers to pass a sort of "visual Turing test." Specifically, the researchers asked both humans and computers to reproduce a series of handwritten characters after being shown just a single example of each; in some cases, subjects were asked to create entirely new characters in the style of those originally shown. Bottom line: human judges couldn't tell the results apart.

The researchers have applied their model to more than 1,600 types of handwritten characters in 50 writing systems, including Sanskrit, Tibetan, Gujarati and Glagolitic. They even tried it on invented characters such as those from the television series "Futurama."

A paper describing the research was published Friday in the journal Science. Its authors were Brenden Lake, a Moore-Sloan Data Science Fellow at New York University; Ruslan Salakhutdinov, an assistant professor of Computer Science at the University of Toronto; and Joshua Tenenbaum, a professor at MIT in the Department of Brain and Cognitive Sciences and the Center for Brains, Minds and Machines.

“It has been very difficult to build machines that require as little data as humans when learning a new concept,” said Salakhutdinov. “Replicating these abilities is an exciting area of research connecting machine learning, statistics, computer vision, and cognitive science.”

Join the newsletter!

Or

Sign up to gain exclusive access to email subscriptions, event invitations, competitions, giveaways, and much more.

Membership is free, and your security and privacy remain protected. View our privacy policy before signing up.

Error: Please check your email address.
Show Comments

Latest Videos

Conversations over a cuppa with CMO: Microsoft's Pip Arthur

​In this latest episode of our conversations over a cuppa with CMO, we catch up with the delightful Pip Arthur, Microsoft Australia's chief marketing officer and communications director, to talk about thinking differently, delivering on B2B connection in the crisis, brand purpose and marketing transformation.

More Videos

The versatility of Live Chat is really what surprises me. I’ve seen it being used not only for customer support, but also as a tool to in...

Drishti Shah

Why Bupa tapped WhatsApp for new customer messaging channel

Read more

Hi This is George, Thanks for sharing this nice information about foodpanda blockchain. During this pandemic situation food delivery indu...

George David

foodpanda launches blockchain-based out-of-home advertising campaign

Read more

Did anyone proofread this document before it was published?

Beau Ushay

CMO Momentum 2020: How to embrace agile marketing

Read more

An honest and hardworking conveyancer doesn't need a marketing strategy. His past clients will spread the word for him. These days the ho...

Bagen Andrea

What this millennial marketer is doing to shake up conveyancing

Read more

Love the post. It is so insightful for companies getting stuck in their habits and missing out on the role innovation can have on revenue...

Alessia Del Genio

How Lego built its culture of innovation, brick by brick

Read more

Blog Posts

Innovate or die

It’s hard to know if famed management and marketing guru, Peter Drucker, coined this phrase for dramatic effect. My belief is he was emphasising the notion that few products and markets are static and few organisations can survive without innovation.

Michael Valos

Senior Lecturer, Department of Marketing, Deakin University

Commissioning personas that get used

How to avoid the bottom drawer, and how to get value from the work you’ve paid for

Melanie Wiese

Chief strategy officer, Wunderman Thompson

Why It’s Going To Be A Bumper Holiday Season Despite the Pandemic

Behavioural science expert Dan Monheit, co-founder and strategy director of creative agency, Hardhat, writes that marketing chiefs should hold their nerve, as they have reason to be optimistic

Dan Monheit

Co-founder, Hardhat

Sign in