'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

Blog Posts

How service heterogeneity is impacting engagement

Marketers have long known the importance of standardising products to assure quality and consistency. For services, however, standardisation is much more complex.

Dr Chris Baumann

Associate professor, Macquarie University

Kindness matters in business: why the nice guys finish first

A recent 1000-page Royal Commission report on misconduct in Australia’s financial sector revealed hair-raising stories of excessive commissions, rampant mis-selling and charges levied on the dead. So how do you stop a bank from misleading its customers?

Nick Liddell

Director of Consulting, The Clearing

Myer vs. David Jones: Do cyborgs win?

As two of Australia’s stalwart brands in Myer and David Jones continue their respective journeys through troubled waters, it heralds yet another sign of the shifting business environment and shift towards an experience economy.

Tom Uhlhorn

Founder and strategy director, Tiny CX

International business is closely related to marketing or marketing activities carried out by the company. According to Gitman and McDani...

Eko Prasetyo Utomo X

Salesforce: The age of the marketing campaign is over

Read more

Back in 1968 Holden began an appeal to customers who have an interest in competition. It did this with the introduction of the HK GTS 32...

Ben Tate

Marketing professor: For Holden, brand nostalgia ain’t what it used to be

Read more

Your blog post is really good and informative. Thanks for taking time to provide us this useful information with us.Auto wrapping uaeADF ...

Yes Machinery

Image intelligence:10 must-see infographics for marketers

Read more

A debt of gratitude is in order for sharing this marvelous information.I have taken in numerous things from your post

digitech Classes

Lumen CMO strives to make the brand synonymous with anti-ageism

Read more

Commercial.

Djordje Milutinovich

​Understanding customer experience from the inside out

Read more

Latest Podcast

More podcasts

Sign in