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 CMO newsletter!

Error: Please check your email address.
Show Comments

Supporting Association

Blog Posts

Marketers are driving our innovation ecosystem

The Government's newly released National Innovation and Science Agenda shows that for economic growth to continue within Australia, an 'innovation ecosystem' must be fostered, where new businesses with new ideas are encouraged to grow and flourish. With every company wanting to increase, retain or improve their customers’ experiences, this makes marketing vital to fuelling Australia's ideas boom.

Lee Tonitto

CEO, Australian Marketing Institute

Putting experience design and strategy in the spotlight

​A few years ago, there was lots of chatter about the elusive UX unicorn; a mythical person capable of delivering everything from research to design to development. It became an obsession for the industry, sparking debate about whether this was the metaphor for how unreasonable our expectations of designers had become, while some felt it was what all designers should be aspiring to.

Tracy Brown

Experience design strategy director, DT

Making sense of artificial intelligence

When new trends and technologies burst onto the marketing scene, there’s always a frantic effort to either keep up or provide guidance, especially when serious amounts of money are involved. It happened with social media, it happened with personalisation and big data, and it’s happening now with artificial intelligence.

Phil Whitehouse

Asia-Pacific innovation lead, DigitasLB

Martech will definitely make everything better especially when it comes to marketing and sales. Any business not comfortable with it shou...

TapAnalytics

Marketo’s CEO talks martech industry consolidation and his enterprise customer ambitions

Read more

You can also try this leads to revenue calculator tool (it's free): https://www.strategic-ic.co.uk...

Fes Askari

​The dangers of misaligning your marketing budget with business goals

Read more

“We wanted to provide was a way for a customer to have a seamless experience as they went across channels,” Marrocco added. “So if your c...

Sarah

​Telstra’s mission to match the offline experience with online customer service

Read more

You have the right to know what happened that made AI possible, after all these years.I discovered and patented statistics on unstructure...

Ilya Geller

Making sense artificial intelligence - Food for thought - CMO Australia

Read more

I hope this trickles down to job opportunities and more analytics based careers on the government.

Ale Xandra

Australian Open details data analytics improvements driving digital fan engagement

Read more

Latest Podcast

More podcasts

Sign in