News > Google

Rolling Study Halls: turning bus time into learning time

Category: Google | Apr 2, 2018

I grew up as an “Army Brat,” a name for kids with a parent in the military who are often on the move. As my mom sums it up, my family spent 18 years on the road in over a dozen cities, 20 different houses, three elementary schools, two middle schools, two high schools—with one tropical fish and one surprise visit from a python in Monterey, CA. Throughout all these travels—meeting people from all different backgrounds, faiths and ethnicities—the highlight was always the excitement of going to a new school. School remains a fixture in my life all these years later.

I’m still a road warrior, traveling across America’s highways and byways for work. On these trips, I see firsthand the growing gap between children living in poverty and those who come from more comfortable circumstances. I meet students who live in remote or rural areas and endure long bus rides to and from school—in some places up to 90 minutes each way. In these areas, like so many others across the country, a lot of students don’t have access to connectivity or devices at home, but they often have schoolwork that requires it. All of this I observe through the lens of technology and its potential to improve lives. Not only does tech enable me to stay connected while I’m on the go, but we live during a time where even astronauts can have Wi-Fi on their space stations. Why couldn’t our students have access to it on their bus rides home?

So in 2016, in partnership with local education leaders in Caldwell County, NC (near our Lenoir Data Center), and some Googler volunteers, we helped install Wi-Fi on 11 school buses in the district. We also worked with the Education Foundation of Caldwell County to make sure there were educators who could accompany students on these Wi-Fi-equipped buses to provide support and help out with assignments. Because bridging the “digital divide” isn’t just about providing access and devices—it’s also about using that technology effectively.

Lilyn Hester speaks at Rolling Study Hall pilot launch in 2016
Lilyn Hester speaking at the Rolling Study Hall pilot launch in 2016

The effects were immediate—almost too immediate for some bus drivers who were shocked (and a little confused) when their commutes became so quiet. Students were engaged. They were learning. And after a few months, there were more real results: School officials saw students do better in school. It was working.

After the success of the pilot, we brought it to another school district—Berkeley County, SC—targeting Lowcountry communities near St. Stephen and Alvin, areas where many students don’t have access at home. We worked with the College of Charleston to do research on the impact of this program and say that after one year, students were significantly more likely to be digitally literate and 80 percent of teacher participants said they were more likely to bring digital lessons into their classroom activities. They also saw homework completion go up, discipline rates go down, and a dramatic increase in overall student engagement.

Because of promising data like this, we’re expanding Rolling Study Halls across the country, starting today in Deer Trail School District in Colorado. As a part of our Grow with Google initiative, Rolling Study Halls will help students across the country access the tools and digital skills they’ll need to be prepared for tomorrow’s workforce.

We’re working with community leaders to outfit buses in 16 additional school districts in partnership with school networking nonprofit CoSN and broadband expert Kajeet. Together we hope to maximize access to learning time outside of school hours, with a goal of reclaiming more than 1.5 million hours for thousands of students by the end of this school year. School districts will be able determine policies to limit access to schoolwork only. Students will also have the chance to work collaboratively—alongside an onboard educator—to complete their assignments.

Introducing Rolling Study Halls

When we first started this program, I wanted to open up opportunities for students in need, and knock down barriers—like lack of access to internet at home—that stood in their way. To see an idea that I started in my own backyard go nationwide is humbling, but we never do it alone. Our program builds on the hard work and dedication of so many teachers, parents, school officials and nonprofit organizations who are making it all possible. And together, we can give these kids access to the learning opportunities they deserve.


Noodle on this: Machine learning that can identify ramen by shop

Category: Google | Apr 2, 2018

There are casual ramen fans and then there are ramen lovers. There are people who are all tonkatsu all the time, and others who swear by tsukemen. And then there’s machine learning, which—based on a recent case study out of Japan—might be the biggest ramen aficionado of them all.

Recently, data scientist Kenji Doi used machine learning models and AutoML Vision to classify bowls of ramen and identify the exact shop each bowl is made at, out of 41 ramen shops, with 95 percent accuracy. Sounds crazy (also delicious), especially when you see what these bowls look like:

Ramen bowls made at three different Ramen Jiro shops.
Ramen bowls made at three different Ramen Jiro shops

With 41 locations around Tokyo, Ramen Jiro is one of the most popular restaurant franchises in Japan, because of its generous portions of toppings, noodles and soup served at low prices. They serve the same basic menu at each shop, and as you can see above, it’s almost impossible for a human (especially if you’re new to Ramen Jiro) to tell what shop each bowl is made at.

But Kenji thought deep learning could discern the minute details that make one shop’s bowl of ramen different from the next. He had already built a machine learning model to classify ramen, but wanted to see if AutoML Vision could do it more efficiently.

AutoML Vision creates customized ML models automatically—to identify animals in the wild, or recognize types of products to improve an online store, or in this case classify ramen. You don’t have to be a data scientist to know how to use it—all you need to do is upload well-labeled images and then click a button. In Kenji’s case, he compiled a set of 48,000 photos of bowls of soup from Ramen Jiro locations, along with labels for each shop, and uploaded them to AutoML Vision. The model took about 24 hours to train, all automatically (although a less accurate, “basic” mode had a model ready in just 18 minutes). The results were impressive: Kenji’s model got 94.5 percentaccuracy on predicting the shop just from the photos.

Confusion matrix of Ramen Jiro shop classifier by AutoML Vision

Confusion matrix of Ramen Jiro shop classifier by AutoML Vision (Advanced mode). Row = actual shop, column = predicted shop. You can see AutoML Vision incorrectly identified the restaurant location in only a couple of instances for each test case.

AutoML Vision is designed for people without ML expertise, but it also speeds things up dramatically for experts. Building a model for ramen classification from scratch would be a time-consuming process requiring multiple steps—labeling, hyperparameter tuning, multiple attempts with different neural net architectures, and even failed training runs—and experience as a data scientist. As Kenji puts it, “With AutoML Vision, a data scientist wouldn’t need to spend a long time training and tuning a model to achieve the best results. This means businesses could scale their AI work even with a limited number of data scientists.” We wrote about another recent example of AutoML Vision at work in this Big Data blog post, which also has more technical details on Kenji’s model.

As for how AutoML detects the differences in ramen, it’s certainly not from the taste. Kenji’s first hypothesis was that the model was looking at the color or shape of the bowl or table—but that seems unlikely, since the model was highly accurate even when each shop used the same bowl and table design. Kenji’s new theory is that the model is accurate enough to distinguish very subtle differences between cuts of the meat, or the way toppings are served. He plans on continuing to experiment with AutoML to see if his theories are true. Sounds like a project that might involve more than a few bowls of ramen. Slurp on.


Harness your Chromebook’s super(charging) powers

Category: Google | Apr 1, 2018

Chromebooks are known and loved for their long battery life, but alas, sometimes you can lose your charger. So the Chrome OS team had a few sparks of creativity to generate renewable ways to keep your Chromebook running anywhere.

Wind power

Next time you’re tap-tapping away on your Chromebook and the low-battery light comes on to taunt you, do the sensible thing: visit the nearest wind tunnel—or, better yet, wind farm—for some free, non-polluting electricity. Pro tip: hold on tight. A full battery is useless if your device gets blown away and smashed to bits.


Solar power

Put summer days to work for you: place your Chromebook in direct sunlight and watch the power level rise. Think of it as a fun-size solar panel. We estimate that 10 minutes should get you going for a good five hours. Unless you use sunblock. That’ll negate all the benefits and leave you with a greasy laptop.


Compost power

A plant-based diet is excellent fuel for your body, but who knew that our leafy friends could provide juice to machines, too? Next time you’re tending the garden, take your Chromebook charger along and watch the battery level grow like a weed.


We hope these alternative-energy sources make it even more convenient to take your Chromebook anywhere and everywhere. Explore the world around you without ever running low on charge!


No laughing matter: Files Go introduces Bad Joke Detector

Category: Google | Apr 1, 2018

Files Go has been helping millions of people around the world free up space on their phone by removing junk files, old apps and forwarded chat media—such as the famous “good morning” memes from India. However, in our most recent research we noticed that there was something else taking up a lot of phone memory. It turns out people are also receiving a lot of very bad jokes from friends and family, leading to lots of daily frustration.

Today we’re proud to introduce the Bad Joke Detector. Using a custom-built deep neural network, Files Go can scan your smartphone for jokes with your permission, identify the bad ones and delete all of them with a single tap, freeing up space for more important things—like better jokes!

Bad Joke Detector - Files Go

We hope this new feature will bring pun back into your life. Give it a try at


Where’s Waldo? Find him in Google Maps

Category: Google | Mar 31, 2018

Hello, friends!

My name is Waldo. I love to travel around the globe—it’s a whole world of fun.

I’m always on the lookout for fantastic new places to explore. My last adventure started in sun-sational Mountain View, CA where I visited the terrific team at Google, including Google Maps product managers Max Greenwald and Shreena Thakore. Wow!

By the way, I’m not traveling on my own. Wherever I go, my trusty friends Wenda, Woof, Wizard Whitebeard, and even that pesky Odlaw go as well. You can come, too—all you have to do is find me!

Starting today, you can use Google Maps to join in my amazing adventures for April Fools this week. Are you prepared for a perplexing pursuit? I’ve shared my location with you on Android, iOS and desktop (rolling out now). To start the search, simply update your app or visit on desktop. Then press play when you see me waving at you from the side of your screen. You can even ask the Google Assistant on your phone, Chromebook or Home device, “Hey Google, Where’s Waldo?” to start.

Waldo Maps GIF

The fun doesn’t stop there. Once you spot me, you’ll be transported to places all around the world, where you can search for me over and over again. Incredible!

You can win wonderful and wacky badges throughout your journey by finding me and my friends. Remember, there’s Woof (but all you can see his is tail), Wenda, Wizard Whitebeard, and Odlaw.

Ready to join me on my travels? If you find me, take a screenshot and share it with @GoogleMaps on Twitter and Instagram with the hashtag #WaldoMaps. Let the journey begin!


The High Five: gathering around the table and in the stands

Category: Google | Mar 30, 2018

Whether celebrating Easter or Passover with friends and family, or cheering on your favorite team, there’s a lot to look forward to this weekend. Here’s a look at some of the top searches from this week, with data from Google News Lab.

Cracking open Easter trends

This weekend, families across the country will gather to celebrate Easter and the beginning of Passover. As this week’s trends show, nothing brings people together like food. Scalloped potatoes and pie top the most-searched recipes for Easter Sunday, and some people are planning for Mass on Saturday: “How long is Easter Vigil Mass?” was one of the top trending Easter-related queries. People are also getting crafty at home in preparation for egg hunts, asking: “how to boil eggs for Easter?”

As for Passover preparations, charoset and brisket were the most popular “Passover Seder recipes,” while search interest in “passover greetings in English” went up 450 percent. Chag sameach!

Taking it to the hole

The NCAA Final Four games are upon us, and Kansas, Kentucky, Nebraska, Michigan and Indiana are the top states searching for “March Madness.” Meanwhile in Illinois, Loyola-Chicago isn’t the only breakout star of the tournament—search interest in their holy good luck charm Sister Jean rose over 1,000 percent this week. People are even wondering “what did Sister Jean give up for Lent?”

Call it a comeback

Search interest in Roseanne Barr spiked over 300 percent on Tuesday, as the 2018 reboot of the popular television series premiered on ABC. Top questions about the show included “who is Jerry on Roseanne?” and “how many people watched Roseanne?” (somewhere in the ballpark of 18 million viewers).

Snap, crackle, pop

“Why are my knuckles cracking?” was a trending question this week. And it was answered by researchers in the U.S. and France who found out it’s caused by tiny bubbles collapsing in the fluid of the joint as the pressure changes. It looks like the three M’s—Minnesota, Michigan and Maryland—are among the top regions searching for “knuckles cracking.” Attempt at your own risk.

Swing batter, batter, swing

Just in time for Major League Baseball’s Opening Day, search interest in “top MLB  prospects for 2018” spiked over 400 percent this week. Top trending teams included the Chicago Cubs, Detroit Tigers and New York Yankees, and Scott Kingery, Salvador Pérez and Vladimir Guerrero Jr. rounded the bases as some of the top trending players.


March into the weekend with talks by inspiring women

Category: Google | Mar 30, 2018

Editor’s Note: Talks at Google is our regular speaker series that brings interesting speakers and brilliant minds from all industries and backgrounds to Google campuses. Each month, we select a few favorite talks from that month, or about a particular topic.

As Women’s History Month comes to a close, we’re re-discovering talks given by women about their breakthrough moments, issues that are important to them, and the strides they’ve made in their fields.

First up, the special guests who stopped by Google New York this International Women’s Day. Oprah, Reese Witherspoon, Ava Duvernay, Storm Reid and Gugu Mbatha-Raw talk about their journey to bring the classic book “A Wrinkle in Time” to the big screen, and chat about why it’s important for women—in the wise words of Mrs. Which—to “find the right frequency.”

Oprah Winfrey, Reese Witherspoon, Ava DuVernay and the cast of Disney "A Wrinkle in Time"

Nathalia Holt wrote “Rise of the Rocket Girls: The Women Who Propelled Us, from Missiles to the Moon to Mars” to tell the stories of the women, known as “human computers,” who broke the boundaries of both gender and science. In her talk, she explains how they transformed rocket design, helped bring about the first American satellites, and made the exploration of the solar system possible.

Nathalia Holt: "Rise of the Rocket Girls"

Oby Ezekwesili, Ibikun Awosika and TY Bello, prominent leaders and advocates in Nigeria, sit down to talk about the glass ceiling, and more importantly, how to smash it. They share thoughts on the limitations placed on women in African societies, and offer advice on how to overcome them–from networking to challenging the status quo. In the words of Oby Ezekwesili, “your strongest weapon is about showing up.”

Oby Ezekwesili, Ibukun Awosika, TY Bello: "Smashing the Glass Ceiling" | Talks at Google

Grace Bonney wrote “In the Company of Women” to share the stories of female entrepreneurs from all industries and walks of life. Claire Mazur, Erica Cerulo and Karen Young are among the women featured in the book, and in this talk, they share their own paths to success and what aspiring entrepreneurs can learn about running creative businesses.

Grace Bonney, Claire Mazur, Erica Cerulo, Karen Young: "In the Company of Women"

Kellee Santiago, former president and co-founder of thegamecompany, shares what it’s like to be a Latina woman in the video game and VR industry and sheds light on unconscious bias and feeling like an outsider. As a bonus: recommendations on her favorite storytelling games.

Hispanic Women and the Video Game Industry


Local entrepreneurs create new opportunities in Kentucky

Category: Google | Mar 30, 2018

Editor’s Note: Grow with Google offers free tools, trainings and events to help people grow their skills, careers, and businesses. The Grow with Google tour brings workshops, one-on-one coaching, and hands-on demos to cities and towns across the United States. Through a series of Keyword posts, we’ll highlight where we’ve been, but you can find out where we’re headed next on our site.

Three years ago, when a coal mine shut down in their hometown of Pikeville, Kentucky, Lynn Parish and Rusty Justice got together to search for a new way forward. They knew that technology could create jobs and enable miners and industry workers to continue living in Pikeville. With courage, determination and ingenuity, Lynn and Rusty created Bit Source, a software development company that would teach miners how to code and then hire them to work as developers. Today, former miners at Bit Source build websites, apps and digital tools for clients across the country.

Bit Source and several other Kentucky-based organizations joined us at the Grow with Google event yesterday in Louisville, where over 700 students, small businesses, educators, budding developers and job seekers participated in workshops, one-on-one coaching, and hands-on demos. These local organizations spoke about the opportunities in tech available to Kentuckians today.

Every 90 days there are about one hundred junior software development opportunities open in the greater Louisville area. Code Louisville is a program created by KentuckianaWorks that offers free software development training to equip people with the skills needed to fill those open jobs. As part of Grow with Google’s ongoing commitment in Louisville, we’re supporting KentuckianaWorks with a $100,000 sponsorship to help the organization expand their efforts, introduce new lessons including the Applied Digital Skills curriculum, and train over 500 new learners.

GwG_Brian Luerman, Anjali Chadha and Justin Hall.jpg
Brian Luerman, Anjali Chadha and Justin Hall share their stories on the Digital Heroes Panel

We’re proud to work alongside Kentuckians like Justin Hall, President of Bit Source, Brian Luerman of KentuckianaWorks, and Anjali Chadha, who at just 15 years old founded Empowered, which teaches young women of color technical skills and pairs them with local businesses who want to expand their online presence.

  • GwG_Louisville1.jpg
    Small business owners participate in the Intro to Online Marketing workshop
  • GwG_Louisville2.jpg
    The Bit Source team snaps a shot at the photo booth with Googler Josh Rosen
  • GwG_Louisville3.jpg
    Young Kentuckians learn together in the Coding for Kids workshop

The Grow with Google tour will come to more cities and towns throughout 2018. Our next two stops are in Savannah, GA on April 25 and Columbia, SC on May 2. Learn more at    


Tip off: how we’re using predictive analytics during the Final Four

Category: Google | Mar 30, 2018

When we teamed up with the NCAA last December, we were thrilled to help them use cloud technology to analyze more than 80 years’ worth of statistical game and competition data. But we also wanted to challenge ourselves to do something a little different in the process—and hopefully delight basketball fans while we were at it.

That’s how we came to embark on a months-long experiment to apply our own technologies to the NCAA’s treasure trove of data. We assembled a team of technicians, data scientists, and basketball enthusiasts (we call them The Wolfpack) who built a data processing workflow using Google Cloud Platform technologies like BigQuery and Cloud Datalab. (For the nitty gritty technical details, read this post on our Big Data blog.)

By analyzing NCAA data through our workflow, we were able to uncover all sorts of interesting facts—everything from who blocks more shots per minute (for the record: juniors) to whether teams with a certain type of animal mascot cause more March Madness upsets (hint: meow). But we wondered if there was more we could do. Could we use data analytics and machine learning to anticipate what might happen during a live game—for example, the number of three-pointers a team might attempt in the second half?

This weekend, we’ll attempt to do exactly that during the Final Four in San Antonio—and we’ll be sharing our predictions in real-time TV ads you can see during halftime. Here’s how it’ll work.

During the Final Four, our Google Cloud team (yes, The Wolfpack included) will be on site in San Antonio, closely following the games. We’ll use our workflow to analyze our observations from the first half of each game against NCAA historical data to hone in on a prediction for the second half that we think is highly probable.

As halftime starts, the real work begins. We’ll have only minutes to turn our prediction into a TV spot. Our creative team will take the prediction generated by our team of data scientists and data analysts and create the ad right there in the Alamodome, using a real-time rendering system built by Cloneless and Eleven Inc. (Fun fact: Cloneless’ rendering system is also built on Google Cloud Platform.)

Before the end of halftime, we’ll hand off our newly-created TV ad to CBS and Turner for airing on TBS right before the beginning of the second half. This is likely the first time a company has used its own real-time predictive analytics to create ads during a live televised sporting event—wish us luck!

One of the exciting things about running an experiment like this in real time is we don’t know for sure what will happen. In this way, it’ll be a little like what it takes to play a game of basketball—thinking on your feet, reacting quickly to new data, and working together as a team. Which, if you think about it, is also true for businesses.

Although this story is about March Madness, we hope it’ll be inspiring well beyond the basketball court. There’s so much to learn from applying cloud technology to data—and that’s true whether you’re an enterprise organization, a nonprofit, or even a sports team.

To learn more, you can check out our site or read our post on the Big Data blog. And if you’re curious to see what happens, tune in to the Final Four on Saturday and Monday to see our predictions as they air. We’ll report back once the tournament is over and let you know what happened—and what we learned. Game on!


New ways to read more with audiobooks from Google Play

Category: Google | Mar 29, 2018

Two months ago we launched audiobooks from Google Play to help you fit more books into your life. Today we have a few updates to make it even easier to enjoy a great book, whether you like to listen on the go with your phone or at home with the Google Assistant on Google Home.

  • Never lose your place with Smart Resume.Interruptions happen all the time, and sometimes you need to pause your audiobook in the middle of a sentence or word because your mom calls or maps tells you to turn in 200 feet. When the book picks back up, you have no idea what’s going on. Smart Resume for audiobooks will intelligently rewind you to the beginning of the word or sentence when you pick up your audiobook again, so you’ll be able to jump right back into where you left off.
  • Revisit your favorite moments with Bookmarks.Now you can save all of your favorite moments with Bookmarks in the Google Play Books app. While listening on Android or iOS device, just tap the bookmark icon to save this spot and revisit your favorite quote anytime.
  • Fit in more reading time with routines on the Google Assistant.Every morning you may type in your work address to Google Maps to see traffic, check your appointments in Google Calendar, and fire up an audiobook for your drive. You can do this all in one step, hands free with the Google Assistant’s support for Routines. In the Google Home app, add audiobooks to your routine. Once added, just say “Ok Google, tell me about my day” for an easy transition into your morning—and your book. 
  • Speed it up—or slow it way down—with greater speed controls.Sometimes you just just can’t wait to figure out whodunnit. Now, you can listen to audiobooks at 3x speed to get through your book even faster, or slow books down to 0.5x in order to really savor the language. The pace is up to you.
  • Share with Family Library in 13 new countries.With Family Library, you can share audiobooks and ebooks with up to five family members for free (depending on the book). Shared books can then be read on Android, iOS and the web. Today, we’re rolling this out to even more families in 13 new countries, including Belgium, Germany, Italy, Netherlands, Norway, Poland, Russia, Spain, Switzerland, Chile, Mexico, Japan (audiobooks only) and South Africa.

These new features are rolling out starting today on Android, iOS, and on devices with the Google Assistant. Time to get back to my book.