Author Archives: Aryn Sanderson

Ask a Techspert: What’s a neural network?

Back in the day, there was a surefire way to tell humans and computers apart: You’d present a picture of a four-legged friend and ask if it was a cat or dog. A computer couldn’t identify felines from canines, but we humans could answer with doggone confidence. 

That all changed about a decade ago thanks to leaps in computer vision and machine learning – specifically,  major advancements in neural networks, which can train computers to learn in a way similar to humans. Today, if you give a computer enough images of cats and dogs and label which is which, it can learn to tell them apart purr-fectly. 

But how exactly do neural networks help computers do this? And what else can — or can’t — they do? To answer these questions and more, I sat down with Google Research’s Maithra Raghu, a research scientist who spends her days helping computer scientists better understand neural networks. Her research helped the Google Health team discover new ways to apply deep learning to assist doctors and their patients.

So, the big question: What’s a neural network?

To understand neural networks, we need to first go back to the basics and understand how they fit into the bigger picture of artificial intelligence (AI). Imagine a Russian nesting doll, Maithra explains. AI would be the largest doll, then within that, there’s machine learning (ML), and within that, neural networks (... and within that, deep neural networks, but we’ll get there soon!).

If you think of AI as the science of making things smart, ML is the subfield of AI focused on making computers smarter by teaching them to learn, instead of hard-coding them. Within that, neural networks are an advanced technique for ML, where you teach computers to learn with algorithms that take inspiration from the human brain.

Your brain fires off groups of neurons that communicate with each other. In an artificial neural network, (the computer type), a “neuron” (which you can think of as a computational unit) is grouped with a bunch of other “neurons” into a layer, and those layers  stack on top of each other. Between each of those layers are connections. The more layers  a neural network has, the “deeper” it is. That’s where the idea of “deep learning” comes from. “Neural networks depart from neuroscience because you have a mathematical element to it,” Maithra explains, “Connections between neurons are numerical values represented by matrices, and training the neural network uses gradient-based algorithms.” 

This might seem complex, but you probably interact with neural networks fairly often — like when you’re scrolling through personalized movie recommendations or chatting with a customer service bot.

So once you’ve set up a neural network, is it ready to go?

Not quite. The next step is training. That’s where the model becomes much more sophisticated. Similar to people, neural networks learn from feedback. If you go back to the cat and dog example, your neural network would look at pictures and start by randomly guessing. You’d label the training data (for example, telling the computer if each picture features a cat or dog), and those labels would provide feedback, telling the neural network when it’s right or wrong. Throughout this process, the neural network’s parameters adjust, and the neural network transitions from not knowing to learning how to identify between cats and dogs.

Why don’t we use neural networks all the time?

“Though neural networks are based on our brains, the way they learn is actually very different from humans,” Maithra says. “Neural networks are usually quite specialized and narrow. This can be useful because, for example, it means a neural network might be able to process medical scans much quicker than a doctor, or spot patterns  a trained expert might not even notice.” 

But because neural networks learn differently from people, there's still a lot that computer scientists don’t know about how they work. Let’s go back to cats versus dogs: If your neural network gives you all the right answers, you might think it’s behaving as intended. But Maithra cautions that neural networks can work in mysterious ways.

“Perhaps your neural network isn’t able to identify between cats and dogs at all – maybe it’s only able to identify between sofas and grass, and all of your pictures of cats happen to be on couches, and all your pictures of dogs are in parks,” she says. “Then, it might seem like it knows the difference when it actually doesn’t.”

That’s why Maithra and other researchers are diving into the internals of neural networks, going deep into their layers and connections, to better understand them – and come up with ways to make them more helpful.

“Neural networks have been transformative for so many industries,” Maithra says, “and I’m excited that we’re going to realize even more profound applications for them moving forward.”

A Googler’s illustrated guide to teamwork

Ah, team projects. They spark dread in the hearts of middle schoolers and business professionals alike. But Googler Stephen Gay, a manager on the Ads User Experience team, says teamwork doesn’t have to be so hard. 

Stephen recently published “Why Always Wins: A Graphic Resource About Leading Teams,” a graphic novel focused on effective leadership. In the conversation below, Stephen talks about writing the book and reveals a few tips for leading high-performing teams.

Where did the idea to create a graphic novel about leadership come from? 

I’ve been so fortunate over the past 20-plus years of my design career to have great coaches and mentors who shared guidance along the way, and I wanted to pay it forward. But, a classic business leadership book is, like, 300 pages of text. In my day job, I’m a user experience (UX) designer, which is all about guiding the user through a journey. I realized that a long book might not be the most engaging format, so I had the idea to put the advice into a more consumable, fun format.

Stephen Gay

Stephen with his graphic novel “Why Always Wins."

How did your day job at Google influence the book? 

For the past two years, I’ve led a team that helps design the UX for Google Ads. Our work allows businesses to create and place ads all over the web, which helps millions of advertisers and publishers. It’s high-impact, high-visibility work, so there’s tremendous pressure to move quickly. 

To do that well, we need to focus on both what we’re doing and how we’re doing it. Research at Google has shown teams with established trust and strong working relationships produce higher-quality work...and at faster speeds.

Screenshot 2019-12-30 at 8.25.14 AM.png


What’s your best advice for leading a high-performing team? 

It’s actually where the title of the book comes from: “Why always wins.” Difficult situations at work inevitably occur, but instead of immediately reacting, it’s important to stop and really assess what’s happening. That starts with self awareness and awareness of the team and the situation.

As a leader, we might come into a situation and want to advocate for our own position right away. Try leading with inquiry, instead of advocacy. Ask why. 

How does asking “why” help? 

Let’s say you notice someone texting on their phone while you’re presenting. Your natural inclination might be to assume they’re not paying attention. By asking why, you might learn that they’re actually dealing with a family emergency or texting a coworker to come check out the presentation because they’re so impressed.

So, if “why always wins,” what always loses? 

“Lose” might be a harsh word, but I see friction and unhealthy tension start to build up in teams when leaders don’t solicit a variety of perspectives. There’s a technique we call the “boomerang” that can help. 

You can bring in the boomerang when a group conversation starts to get heated, typically between two people. To boomerang it, you throw the question back out to the rest of the group to collect everyone’s opinions and then formulate a next step. At Google, we talk a lot about creating a culture of inclusivity, and the boomerang is an easy technique to open the conversation back up to more perspectives, and especially allow quieter voices to be heard. 

Why Always Wins


Besides “why,” what’s a key phrase leaders should get comfortable with? 

Not speaking at all. There’s a lot of power in a pause. One of my early mentors used to say, “Sometimes you have to go slow to go fast.” When you’re in a heightened state of confusion or frustration and speak rashly, you can make bad decisions. Sometimes you need a moment for the water to clear, and then you can guide your team forward in a more mindful way.