Google AI project apes memory, programs (sort of) like a human

Neural Turing Machines attempt to emulate the brain's short-term memory

Artificial intelligence concept illustration

An artificial intelligence concept illustration.

abstract, android, artificial, binary, blue, brain, cell, communication, computer, concept, connection, creative, cyber, cybernetic, cyberspace, cyborg, data, digit, digital, fantasy, fiction, future, futuristic, fuzzy, head, human, idea, illustration, imagination, informatics, information, dreamstime

dreamstime_29416761
Artificial intelligence concept illustration An artificial intelligence concept illustration. abstract, android, artificial, binary, blue, brain, cell, communication, computer, concept, connection, creative, cyber, cybernetic, cyberspace, cyborg, data, digit, digital, fantasy, fiction, future, futuristic, fuzzy, head, human, idea, illustration, imagination, informatics, information, dreamstime dreamstime_29416761

The mission of Google's DeepMind Technologies startup is to "solve intelligence." Now, researchers there have developed an artificial intelligence system that can mimic some of the brain's memory skills and even program like a human.

The researchers developed a kind of neural network that can use external memory, allowing it to learn and perform tasks based on stored data.

Neural networks are interconnected computational "neurons." While conventional neural networks have lacked readable and writeable memory, they have been used in machine learning and pattern-recognition applications such as computer vision and speech recognition.

The so-called Neural Turing Machine (NTM) that DeepMind researchers have been working on combines a neural network controller with a memory bank, giving it the ability to learn to store and retrieve information.

The system's name refers to computer pioneer Alan Turing's formulation of computers as machines having working memory for storage and retrieval of data.

The researchers put the NTM through a series of tests including tasks such as copying and sorting blocks of data. Compared to a conventional neural net, the NTM was able to learn faster and copy longer data sequences with fewer errors. They found that its approach to the problem was comparable to that of a human programmer working in a low-level programming language.

The NTM "can infer simple algorithms such as copying, sorting and associative recall from input and output examples," DeepMind's Alex Graves, Greg Wayne and Ivo Danihelka wrote in a research paper available on the arXiv repository.

"Our experiments demonstrate that it is capable of learning simple algorithms from example data and of using these algorithms to generalize well outside its training regime."

A spokesman for Google declined to provide more information about the project, saying only that the research is "quite a few layers down from practical applications."

In a 2013 paper, Graves and colleagues showed how they had used a technique known as deep reinforcement learning to get DeepMind software to learn to play seven classic Atari 2600 video games, some better than a human expert, with the only input being information visible on the game screen.

Google confirmed earlier this year that it had acquired London-based DeepMind Technologies, founded in 2011 as an artificial intelligence company. The move is expected to have a major role in advancing the search giant's research into robotics, self-driving cars and smart-home technologies.

More recently, DeepMind co-founder Demis Hassabis wrote in a blog post that Google is partnering with artificial intelligence researchers from Oxford University to study topics including image recognition and natural language understanding.

Join the newsletter!

Or

Sign up to gain exclusive access to email subscriptions, event invitations, competitions, giveaways, and much more.

Membership is free, and your security and privacy remain protected. View our privacy policy before signing up.

Error: Please check your email address.
Show Comments

Blog Posts

3 skills you need to drive better collaboration

A study published in The Harvard Business Review found the time spent in collaborative activities at work has increased by over 50 per cent in the past two decades. Larger projects; complicated problems; tighter timeframes: These require bigger teams with specialised skillsets and diverse backgrounds, often dispersed globally.

Jen Jackson

CEO, Everyday Massive

Better the bank you know?

In 2018, only 21 per cent of customers believed that banks in general had their customers best interests at heart and behave ethically. Only 26 per cent believed that banks will keep their promises; views cemented further following the Hayne Financial Services Royal Commission.

Carolyn Pitt

Head of account management, Hulsbosch

What 15 years of emotional intelligence told us about youth media audiences

Taking people on an emotional journey through content is the most critical part of being a publisher. Which is why emotion lies at the heart of VICE Media.

Stephanie Winkler

Head of insights, VICE Asia-Pacific

It's a pretty good idea. I think this integration is useful. Don't you agree?

Misty Stoll

Officeworks hops on voice interface bandwagon with Google Assistant integration

Read more

ok. so no RCS support? by the way, RCS is a lot bigger than 5G in terms of marketing and monetisation so y'all should be covering it.

DragoCubed

Optus goes for education with 5G network campaign

Read more

Many companies and individual merchants have shifted their major part of marketing to web marketing services Portland as it weighs fewer ...

Radiata Solutions

6 Ways to ramp up Social Media to Your Web Design

Read more

This is a unique experience! Will be interesting to talk to their managers.

Joyce Harris

​How Krispy Kreme revitalised its brand in a saturated market

Read more

I feel bad for them. It's a shame they are closed now. What do you think about it?

Lisa Deleon

Dick Smith stores set to all close by 30 April

Read more

Latest Podcast

More podcasts

Sign in