Menu
MIT's Picture language could be worth a thousand lines of code

MIT's Picture language could be worth a thousand lines of code

MIT has developed a probabilistic programming language that could take same the grunt work out of machine learning

MIT's new work in probabilistic programming allows a computer to recognize a face through inference.

MIT's new work in probabilistic programming allows a computer to recognize a face through inference.

Now that machine-learning algorithms are moving into mainstream computing, the Massachusetts Institute of Technology is preparing a way to make it easier to use the technique in everyday programming.

In June, MIT researchers will present a new programming language, called Picture, that could radically reduce the amount of coding needed to help computers recognize objects in images and video. It is a prototype of how a relatively novel form of programming, called probabilistic programming, could reduce the amount of code needed for such complex tasks.

In one test of the new language, the researchers were able to cut thousands of lines of code in one image recognition program down to fewer than 50. They plan to present the results at the Computer Vision and Pattern Recognition conference in June

With probabilistic programming, "we're building models of what faces look like in general, and use them to make pretty good guesses about what face we're seeing for the first time," said Josh Tenenbaum, an MIT professor of computational cognitive science who assisted in the work.

Picture uses statistical inference to cut away much of the basic computational work needed for computer vision. It works much like the inverse to computer animation. Computer graphics programs, such as those used by Pixar and other animation companies, make two-dimensional representations of three-dimensional objects, given a relatively small amount of instruction from programmers. The Picture language works in the opposite direction. It can recognize an object within a two-dimensional image by comparing it to a set of models of what the objects could be.

The work stems from a program that the U.S. Defense Advanced Research Projects Agency launched in 2013 to develop probabilistic programming languages to further facilitate the use of machine learning.

Although an academic pursuit for decades, machine learning is quickly becoming a feasible technique for commercial use, thanks to more powerful computers and new cloud machine learning services offered by Amazon Web Services and Microsoft Azure.

Although probabilistic programming does not require machine learning to work, it can provide a way to streamline the use of machine learning, Tenenbaum said.

"In pure machine learning, you drive performance increases by just collecting more and more data and just letting machine learning do the work," Tenenbaum said. In probabilistic programming, "the underlying system is more knowledge-based, using the causal process of how images are formed," Tenenbaum said.

Picture is one of a number of different probabilistic programming languages that MIT is currently working on. Another, more general-use, probabilistic programming language from the team, called Venture, can be used to solve other kinds of problems, Tenenbaum said.

Joab Jackson covers enterprise software and general technology breaking news for The IDG News Service. Follow Joab on Twitter at @Joab_Jackson. Joab's e-mail address is Joab_Jackson@idg.com


Follow Us

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.

Tags softwareapplication developmentDevelopment toolsLanguages and standardsMassachusetts Institute of Technology

Featured

Slideshows

The making of an MSSP: a blueprint for growth in NZ

The making of an MSSP: a blueprint for growth in NZ

Partners are actively building out security practices and services to match, yet remain challenged by a lack of guidance in the market. This exclusive Reseller News Roundtable - in association with Sophos - assessed the making of an MSSP, outlining the blueprint for growth and how partners can differentiate in New Zealand.

The making of an MSSP: a blueprint for growth in NZ
Reseller News Platinum Club celebrates leading partners in 2018

Reseller News Platinum Club celebrates leading partners in 2018

The leading players of the New Zealand channel came together to celebrate a year of achievement at the inaugural Reseller News Platinum Club lunch in Auckland. Following the Reseller News Innovation Awards, Platinum Club provides a platform to showcase the top performing partners and start-ups of the past 12 months, with more than ​​50 organisations in the spotlight.​​​

Reseller News Platinum Club celebrates leading partners in 2018
Meet the top performing HP partners in NZ

Meet the top performing HP partners in NZ

HP has honoured its leading partners in New Zealand during 2018, following 12 months of growth through the local channel. Unveiled during the fourth running of the ceremony in Auckland, the awards recognise and celebrate excellence, growth, consistency and engagement of standout Kiwi partners.

Meet the top performing HP partners in NZ
Show Comments