'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

Data has the power to build or burn brands

A brand can be severely wounded by use or misuse of any of its assets and you could say data has the greatest power of all to inflict damage.

Lucy Acheson

Head of data strategy and customer experience, LIDA

Totto and your inorganic future

At Cannes Lions this year we’ve been treated to many artificial intelligence (AI) insights. It’s one of the major discourses of our time.

Richard Brett

CEO, opr

Personas of one and the rise of ‘always there’ marketing

I’ve got some bad news. The ‘always on’ marketing approach that many companies have only just fully implemented is already out of date.

Nigel Roberts

Founding partner and strategy lead, Yell

Machine learning represents the future for digital marketing. I'm glad that there are strides being made in this direction and that even ...

Claudia Evans

Looker eyes benefits of machine learning to connect with customers

Read more

I read you post full. It's really good .

Yusuf

Salesforce ups the Marketing Cloud ante with Datorama acquisition

Read more

Promotion is difficult. You should be able to do it. Sometimes it turns out bad, and when you turn to professionals, it turns out well - ...

Jordan Samuil

Village Roadshow partners with Lion for pourage rights and promotional partnership

Read more

This is very good news for Australian SMEs as ActiveCampaign is an very powerful marketing automation / email marketing tool that costs a...

Lawrence

SMB marketing automation provider sets up Asia Pac HQ in Sydney

Read more

Completely agree! For the best commercial properties in Mumbai, visit our website - Jagaha!

Gizelle

Salesforce ups the Marketing Cloud ante with Datorama acquisition

Read more

Latest Podcast

More podcasts

Sign in