'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 CMO newsletter!

Error: Please check your email address.
Show Comments

Supporting Association

Blog Posts

Disruption Down Under – What’s Amazon’s real competitive advantage?

Savvy shoppers wait in anticipation, while Australian retailers are gearing up for the onslaught. Amazon’s arrival is imminent.

Change across the board: Why boards need to digitally evolve

Traditionally the non-executive board of a company acts in an advisory capacity - attending monthly board meetings to offer overarching advice and guidance typically focusing on:

Jodie Sangster

CEO, ADMA

The most desirable customers you’ve overlooked

“What will really move the needle?” This is a question that keeps leaders awake at night. And at the intersection of some of their top priorities – finding pockets of growth, redefining the customer experience, and making an emotional impact – lies a latent market: Their diverse customers.

Being aware of regulations or guidlines is just the start. As our CEO Emma Lo Russo stated exactly two weeks ago at an event we supported...

Alan Smith

​Are the Wild West days of influencer collaboration over?

Read more

Rebranding is always nice solution to get better organisation. Businessman may apply certain special services (for example, https://www.l...

David Hill

CMO interview: Spearheading the global rebranding of OFX

Read more

Thank you so much for sharing this article.Top Digital Marketing company in Bangalore

Way To DM

Predictions: 17 digital marketing trends for 2017

Read more

Thanks for the great article Jodie, agree many boards and senior execs are operating in outdated modes, just as we need some reverse soci...

sharyn

Change across the board: Why boards need to digitally evolve - Data-driven marketing - CMO Australia

Read more

I'm looking forward to Marketo moving toward providing these type of engagement metrics. The vision is there - what happens next to the p...

Emily Dick

Marketo CEO: Stop using outdated metrics, start basing marketing on engagement

Read more

Latest Podcast

More podcasts

Sign in