Connect with us

Google

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…

Published

on

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.”

Source

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published.

Google

Countering hack-for-hire groups

As part of TAG’s mission to counter serious threats to Google and our users, we’ve published analysis on a range of persistent threats including government-backed attackers, commercial surveillance vendors, and serious criminal operators. Today, we’re sharing intelligence on a segment of attackers we call hack-for-hire, whose niche focuses on compromising accounts and exfiltrating data as…

Published

on

By

As part of TAG’s mission to counter serious threats to Google and our users, we’ve published analysis on a range of persistent threats including government-backed attackers, commercial surveillance vendors, and serious criminal operators. Today, we’re sharing intelligence on a segment of attackers we call hack-for-hire, whose niche focuses on compromising accounts and exfiltrating data as a service.

In contrast to commercial surveillance vendors, who we generally observe selling a capability for the end user to operate, hack-for-hire firms conduct attacks themselves. They target a wide range of users and opportunistically take advantage of known security flaws when undertaking their campaigns. Both, however, enable attacks by those who would otherwise lack the capabilities to do so.

We have seen hack-for-hire groups target human rights and political activists, journalists, and other high-risk users around the world, putting their privacy, safety and security at risk. They also conduct corporate espionage, handily obscuring their clients’ role.

To help users and defenders, we will provide examples of the hack-for-hire ecosystem from India, Russia, and the United Arab Emirates and context around their capabilities and persistence mechanisms.

Source

Continue Reading

Google

Preserving languages and the stories behind them

Our Potawatomi tribe partner, Justin Neely, is using Woolaroo to promote and preserve the Potawatomi’s language, Bodéwadmimwen, among students and young people. “Words, phrases and verb conjugations show how the Potawatomi see the world — with an emphasis on connection to the earth, a high regard for mother nature and living beings, and a communal…

Published

on

By

Our Potawatomi tribe partner, Justin Neely, is using Woolaroo to promote and preserve the Potawatomi’s language, Bodéwadmimwen, among students and young people. “Words, phrases and verb conjugations show how the Potawatomi see the world — with an emphasis on connection to the earth, a high regard for mother nature and living beings, and a communal lifestyle,” says Neely. Neely felt that Woolaroo would suit children in particular, allowing them to use technology as a way to explore their heritage.

Source

Continue Reading

Google

Go on an epic adventure with Netflix’s “The Sea Beast”

Craving a different type of drive this summer? Go on a high-seas adventure without stepping off land. Activate Waze’s latest driving experience, inspired by Netflix’s newest movie, “The Sea Beast.” (Check out the trailer and the film on Netflix July 8.)Starting today, you’ll meet the dynamic duo of Maisie, a precocious stowaway, and Blue, a…

Published

on

By

Craving a different type of drive this summer? Go on a high-seas adventure without stepping off land. Activate Waze’s latest driving experience, inspired by Netflix’s newest movie,The Sea Beast.” (Check out the trailer and the film on Netflix July 8.)

Starting today, you’ll meet the dynamic duo of Maisie, a precocious stowaway, and Blue, a little beast with a huge mischief streak, and revel in the unlikely comedy of their friendship as they help you navigate every turn you take on Waze. And don’t worry: Maisie will help translate Blue’s sounds for you. You’ll also get to know some other Beasts that they find on their journey when you choose between three new Moods: Blue, Red and Yellow. Don’t forget to swap your vehicle for a Lifeboat, to get into the true adventurer’s spirit.

With Sea Beast Mode activated, get ready to explore the world together, on a journey full of surprise, wonder and funny banter — because where the map ends, the adventure begins.

If you’re interested in seeing the magic in real life, Netflix is hosting a series of experiences across the U.S. at aquariums, museums and more to celebrate the launch of The Sea Beast.

For a drive that takes you to the seas, visit Waze or click “My Waze” in your Waze app and tap the “Turn on Sea Beast Mode” banner to activate. It’s available globally, in English, for a limited time.

Source

Continue Reading

Trending

Copyright © 2021 Today's Digital.