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 marketing mistakes to overcome when courting prospective customers

Marketing that urges respondents to ‘buy now’ is a little like asking someone to marry you on your first date. At any time, only 3 per cent of the market is looking for what you’re selling, so the chances of your date randomly being ‘The One’ is pretty slim.

Sabri Suby

Founder, King Kong

Why are we dubious about deep learning?

The prospect of deep learning gives those of us in the industry something to get really excited about, and something to be nervous about, at the same time.

Katja Forbes

Founder and chief, sfyte

Why you can’t afford to fail at CX in 2019

In 1976 Apple launched. The business would go on to change the game, setting the bar for customer experience (CX). Seamless customer experience and intuitive designs gave customers exactly what they wanted, making other service experiences pale in comparison.

Damian Kernahan

Founder and CEO, Proto Partners

Red Agency YouGov Galaxy Report, February 2019 Predictors Study. https://redagency.com.au/re...

Vanessa Skye Mitchell

DNA-based marketing: The next big thing?

Read more

RIP holden

Max Polding

Marketing professor: For Holden, brand nostalgia ain’t what it used to be

Read more

Where does the claim that 2 million Australians have tested come from ? Anecdotal information suggests that this is way off the mark.

David Andersen

DNA-based marketing: The next big thing?

Read more

Thank you for the info , being part of a digital marketing agency in kerala , this proved handy and get to know with upcoming trends. htt...

Dotz Web Technologies

Predictions: 9 digital marketing trends for 2019

Read more

So who then is correct? The Research or The skilled Digital people.

Anene

Report reveals Australia faces digital skills shortage

Read more

Latest Podcast

More podcasts

Sign in