Android Police

Articles Tagged:

machine learning


Here are a few ways machine learning has improved Gboard

Google has been improving Gboard with the same type of tools it uses for speech recognition: machine learning. The budding technology is rapidly becoming a ubiquitous method for improving results and performance. If a network can be trained to accurately accomplish something in a performant way, odds are you'll see it introduced to any product it can be applied to. Gboard and text-input as a whole are no different, and we are reaping the benefits of improved corrections and predictions every time we swipe out a low-accuracy message to a friend. But how do these improvements work?

Read More

Amazon releases the Android companion app for its fashion-focused Echo Look

We might have previously thought that it was an April Fools' joke, given the timing, but Amazon's Echo Look is quite real. The device, with its camera and fancy machine learning skills, is meant to add some fashion sense to Amazon's personal assistant. It is able to judge contemporary styling between a pair of outfits and even allows you to save your favorites. Today Amazon released the companion app for the Echo Look on Android, so now users of our favorite operating system can see on their phone which headband went better with that Blue Steel look.

Read More

The Quick Access feature in Google Drive for Android is coming to Drive on the web


Android O feature spotlight: Smart Text Selection automatically highlights the right words at a double tap

One of the new features in Android O that was recently announced at I/O is Smart Text Selection. Selecting the right text can be hard on a small screen, but Google's data shows that most of the time when we are selecting information it's something like an address or phone number. Now in Android O you can double tap text, and the selection automatically expands as needed. It even shows a convenient predictive shortcut so we can use it in another context, or save it. Of course, we can use the Assistant to do all those things if we remember, but it's good to have multiple ways of solving the same problem.

Read More

Suggested Sharing, Shared Libraries, and photo books in Google Photos utilize machine learning to group photos together

Google Photos is something many people use every day; the automatic backup feature is so convenient, and the free unlimited storage is a major selling point. At I/O 2017, Google unveiled three new features: Suggested Sharing, Shared Libraries, and photo books. All of these use Photos' excellent machine learning technology to group faces together.

Read More

The robots are winning: Google's neural network OCR gives names to the nameless (streets)

Everyone uses Google Maps, but not often do we consider where, exactly, all that data comes from. When a new road goes in, or a bypass, or the name of a street changes, it isn't as if your local city reaches out to Google to make sure everything is up to date. Some of that used to come from user submissions in the Map Maker forum. Now those tools are being rolled into Maps itself, but that's not the only source of information. Google's fleets of Street View cars collect an insane number of images, and nestled in with them are pictures of businesses, street signs, and addresses, and Google's latest research blog post goes into some interesting details about all that potential data.

Read More

Google AutoDraw uses machine learning to make a designer out of anyone

The latest experiment to come out of Google Creative Lab is a web-based tool that uses machine learning to help you with all your design needs. If you need to fire off a quick design for a birthday card or an event poster, AutoDraw has you covered.

Using the simple MSPaint-style interface, all you have to do is draw a rudimentary outline of whatever you would like, and the suggestion tool will guess what you’re drawing and offer you far more professional looking alternatives. Click on a suggestion and it automatically replaces your inferior handiwork with something much prettier, sourced from various talented artists, designers, and illustrators.

Read More

Google introduces Perspective, a machine learning initiative to help police comments

I've said before that comments on internet posts are a double-edged sword; on the one hand, you can have fantastic conversations with them or you get a toxic cesspit with people spitting whatever drivel comes to mind. Google is hoping to combat the latter with its newest machine learning initiative called Perspective.

Read More

Google's A.I. Duet will respond to music you play

Everyone enjoys making music of some kind, from children hitting pots and pans together to an experienced musician performing to a sell-out crowd. I'm tone deaf and even I enjoy it. Today, Google announced it has a new experiment, A.I. Duet, which uses machine learning to respond to music that you play.

A.I. Duet was built by developer and musician Yotam Mann, based on the Magenta framework Google released last year. Using this, he's been able to have artificial intelligence learn how to play music based on hundreds or thousands of samples, through machine learning. While computers have been able to play music for a while, they would have to have been taught how to play.

Read More

Google's TensorFlow hits v1.0 with upgrades to speed, flexibility, and production-readiness

At the TensorFlow Developer Summit, Google announced that its second-generation machine learning platform has reached the v1.0 milestone. In the time since it went open-source, TensorFlow has helped many professionals in several fields make huge strides in things like language translation, early skin cancer detection, and diabetic blindness prevention.

Read More