Facebook AI Software Learns and Answers Questions

Software able to read a synopsis of Lord of the Rings and answer questions about it could beef up Facebook search.

Facebook is working on artificial intelligence software that can process text and then answer questions about it. The effort could eventually lead to anything from better search on Facebook itself to more accurate and useful personal assistant software.

The social network’s chief technology officer, Mike Schroepfer, introduced the software, called Memory Network, in a talk at Facebook’s F8 developer conference in San Francisco on Thursday. He demonstrated how the software could acquire knowledge from text by showing how it was fed a super-simple synopsis of the book “Lord of the Rings”, in the form of phrases including “Bilbo travelled to the cave” and “Gollum dropped the ring there.” After that, the software could answer questions that required following the flow of events in the text, such as “Where is the ring?” and “Where is Frodo now?”

Extracting information from text and figuring out how to put it together into brand-new facts is a difficult task for computers to do–as Shroepfer noted in his demo, it requires the machine to understand the relationships between objects over time.

Facebook is making this work with a new twist on a recently-popular approach to machine learning called deep learning (see “10 Breakthrough Technologies 2014: Deep Learning”). That technique involves using networks of crude “neurons” to process data. Facebook added what Schroepfer described as a “multimillion-slot memory system” to such a network, which functions essentially as a short-term memory where facts can be stored and processed.

Facebook set up a research group dedicated to deep learning in 2013 (see “Facebook Launches Advanced AI Effort”). Like similar groups at Google and elsewhere, it has largely focused on using the technique to make software able to figure out what’s going on in images. In his talk, Schroepfer also showed results from a project in which his researchers taught deep learning software to classify 487 different sports from looking at video clips. He said it is good enough to differentiate between figure skating, speed skating, artistic roller skating, and ice hockey.

That such an apparently easy task is a major achievement for software is a reminder that even deep learning software is far from very intelligent. Such software could be valuable, though. If applied to the many videos uploaded to Facebook, it might make it possible to, say, show you ads that are closely targeted to what you’re watching.

View the original article here

Facebook Lets Developers Build on Its Chat App

Facebook hopes that adding functionality like video sharing and shopping to Messenger will help it grow even as competition rises.

Facebook is responding to the growing popularity of mobile messaging apps by giving its own messaging app new capabilities. The company will let developers make their apps work within Facebook Messenger, and is also making it possible for shoppers to chat with businesses using the app.

During a presentation at the social network’s F8 developer conference in San Francisco on Wednesday, Facebook founder and CEO Mark Zuckerberg said Facebook wants to make it easier for Messenger’s 600 million users to share more content—animated GIFs, videos, or animated greeting cards, for example—through Messenger itself, rather than by leaving the chat app. To do that, Facebook is rolling out Messenger Platform, which developers can use to make Messenger apps for sharing various kinds of media.

You can already share photos, videos, stickers, and maps of your location over Messenger, as well as make voice calls through the app and, as of recently, send money to another user. But allowing outside developers to integrate with the app could give Messenger an advantage over newer chat apps like WeChat and Snapchat.

In a demo, Facebook’s Messenger head, David Marcus, pointed out a three-dot icon near the bottom of the Messenger screen on a smartphone; pressing it yielded a list of apps already installed for use with Messenger (in this case, a personalized emoji-maker called Bitmoji and a text customizer and animator called Legend). Users can create an animated expression like “I’m so excited!” using Legend, for example, and send it through Messenger to a friend who will be able to see it even if they don’t have the Legend app. Marcus also showed how other apps could be installed from a Messenger app store.

Messenger Platform became available Wednesday, and Marcus said that more than 40 apps are participating.

Facebook also unveiled a plan to let businesses chat with customers in a new way. The hope is that when you’re buying something online, a retailer will let you choose to be contacted via Messenger about your order, and if you assent, you can see an order confirmation, shipping details, and other information in the app. You’ll even be able to do things like change your order or, as a demo with online clothing retailer Everlane indicated, buy additional items via chat.

Everlane and daily-deal clothing site Zulily will be among the first companies using the service in the next few weeks, and additional merchants will be added in the coming months.

View the original article here

Facebook means business with Messenger Platform, VR and drones

document.write(calculate_time('29 Mar 2015, 18:16'));Samsung has recently showcased us the Galaxy S6 and S6 Edge in India. Both these devices are available in 32GB / 64GB / 128GB capacity and already on pre-order in India.

document.write(calculate_time('29 Mar 2015, 17:59'));Meerkat is reportedly getting ready to make some changes to its app in order to better compete with Periscope, the live streaming app that Twitter just scooped up earlier this month.

document.write(calculate_time('29 Mar 2015, 17:43'));HTC has let details of the One E9+ slip on its Chinese website, but something doesn't quite add up.

document.write(calculate_time('29 Mar 2015, 17:34'));Back at the Google I/O developer conference in June 2014, Google officially unveiled the Android One project, a program in which Google would work hand-in-hand with low-cost smartphone manufacturers in emerging markets.

document.write(calculate_time('29 Mar 2015, 17:30'));We answer the age-old question of whether you should build or buy your gaming rig.

document.write(calculate_time('29 Mar 2015, 16:00'));From Richey Edwards's love of John Madden's American Football to Massive Attack's Kick Off 2 addition.

document.write(calculate_time('29 Mar 2015, 15:30'));Cover the country properly before boasting about tiny pockets of lab-perfect 4G.

document.write(calculate_time('29 Mar 2015, 12:50'));Whilst VR inevitably dominated the company's F8 developer conference, Messenger Platform was a big move on the business front.

document.write(calculate_time('29 Mar 2015, 05:11'));World's first dual-curved glass display is almost here, and it's an idea that is here to stay.

document.write(calculate_time('28 Mar 2015, 20:30'));We venture to a galaxy far, far away to highlight the greatest Star Wars games to ever hit the PC.

document.write(calculate_time('28 Mar 2015, 19:30'));We look at what pieces of virtual reality tech are likely to change PC gaming forever, and the problems some genres present to VR.

document.write(calculate_time('28 Mar 2015, 18:30'));And why Apple might have made a slghtly better running watch than we all thought

document.write(calculate_time('28 Mar 2015, 18:30'));Are there really any differences between the two technologies that aim to smooth your PC games?

document.write(calculate_time('28 Mar 2015, 18:00'));Remembering Ocean's surreal platformer through Amiga Power's 1991 review.

document.write(calculate_time('28 Mar 2015, 16:31'));These are the television shows you need to be watching on Amazon Prime right now.

document.write(calculate_time('28 Mar 2015, 16:08'));Talking the future of game design with some of the most important names in the business.

document.write(calculate_time('28 Mar 2015, 15:30'));And why Bloodborne has made me a loner.

document.write(calculate_time('28 Mar 2015, 15:30'));For years, Mac gaming has been almost an oxymoron - not really worth considering if your love of games extends beyond Football Manager. But things are changing.

document.write(calculate_time('28 Mar 2015, 15:20'));Star Citizen is a game of almost unfathomable scope, from the creator of the classic Wing Commander, Chris Roberts.

document.write(calculate_time('28 Mar 2015, 14:36'));If James Bond had an external hard drive in his Aston Martin, it would be the Seagate Seven.Load more

View the original article here

The Facebook Page That Posts the Same Picture Every Day

A Facebook page that posts the same picture of an Italian singer every day has become the central part of a research project to understand how we use social media.

On the Italian language version of Facebook, a curious page came into existence in latter half of 2014. This page is devoted to Toto Cutugno, an Italian singer and song-writer who is famous in the part of the world. Every day, the owner of this page posts a picture of Cutugno, indeed, the same picture every day.

This page is imaginatively entitled “La stessa foto di Toto Cutugno ogni giorno” meaning “The same photo of Toto Cutugno every day”. And it’s easy to imagine that it might attract little attention from the Facebook crowd.

Not so. The posts on this page have received almost 300,000 likes, 14,000 comments and been shared more than 7000 times. It’s fair to say it has a cult following, despite the homogeneity of its content.

That has piqued the interest of Alessandro Bessi at the Institute for Advanced Study in Pavia, Italy and few pals, who have made this page a central part of their research. These guys have been studying the way people consume content on social media sites and say that the Toto Cutugno page is the perfect control for their experiments.

The reasons are straightforward. Most of the pages this team is interested in host a wide range of different posts. These posts attract varying levels of interest in the form of likes, shares and comments. But exactly how this interest depends on the content is hard to tease apart.

What’s needed is a control page that always posts the same content so that the team can assess the background level of interest. Enter “La stessa foto di Toto Cutugno ogni giorno”. This page allows the team to see how users interact with a page when the content is held constant.

Bessi and co have compared the way people use this page with 73 public Facebook pages, 34 of them about science and 39 of them about conspiracy theories. They start by counting the number of likes for that each user gives to the pages visited. It turns out that this produces a power law or heavy-tailed distribution in which most users give a small number of likes while a few dish out a very large number. Curiously, the users of all the pages—the conspiracy theory pages, the science pages and the control page—follow this same pattern.

The team also looked at the lifetime of these users—for how long they continued to like pages. Once again the users of all pages follow a similar pattern, although users of the control page show some differences, such as more who continue to like the page for very long periods.

The big difference between the way people use these pages is in the number of likes each post receives. This follows a heavy tailed distribution for the conspiracy and science pages—so most pages receive a few likes but a few receive a great deal of them.

One of the features of this kind of distribution is that the concept of an “average” page makes no sense. In a normal distribution, the average coincides with the peak of the curve and so represents an important quantity about the data. This is useful when talking about the average height of adult men and women or their average weight and so on.

But there is no peak in a heavy-tailed distribution so the concept of an average makes no sense. That’s why people never talk about an average-sized earthquake or forest fire or flu outbreak, the sizes of which all follow heavy-tailed distributions.

That’s relevant because the way people “like” posts on the control page is entirely different to the way they “like” other posts. This follows something like a normal distribution in which there is a clear average number of likes.

That reveals something important about the way people like the control page—that the number of likes for any post clusters around some average value.

Just why this is the case, Bessi and co do not say. But it’s easy to speculate. The “La stessa foto di Toto Cutugno ogni giorno” page obviously attracts fans of the eponymous Cutugno, who are clearly limited in number. It is this limit that prevents any posts receiving the very large numbers of likes that are characteristic of a heavy tailed distribution.

Bessi and co go on to simulate the way people like each type of page and say they can capture this behaviour with a relatively simple model. “We show that the proposed model is able to reproduce the phenomenon observed from empirical data,” they say.

Just how useful this will be for future studies isn’t clear.  Nevertheless, Cutugno himself must be flattered at the scientific attention his image has generated.

Ref: arxiv.org/abs/1501.07201  Everyday the Same Picture: Popularity and Content Diversity

View the original article here