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

Should your disclaimer become your headline?

To avoid misleading customers, or simply through fear of legal backlash, advertising has evolved to hide the potential shortcomings of an offer in its disclaimer.

Sam Tatam

Head of behavioural science, OgilvyChange Australia

The evolving role of the CMO

They say that “change is the only constant”. It’s fair to say that in the 20 years I’ve been in marketing positions, the role of the CMO has changed completely.

Tim Tez

Chief product and marketing officer, MetLife

Transform your marketing analytics to outperform your competition

As digital and offline brand experiences diversify, more customer data is becoming available to marketers. At the same time, the number of tools available to analyse this data is increasing rapidly. Leading marketers are taking advantages of these shifts and transforming their marketing analytics practices to outperform their competitors.

Working with Kim was an absolute career highlight for me. She is creative, strategic, innovative and a forward thinker. She is a true l...

Anonymous

Helloworld scraps CMO role

Read more

It's the biggest disappointment for me because i mostly use whatsapp and separate it from my facebook account. I use high level encryptio...

amiron carro

Facebook will use Whatsapp users' personal data to target ads

Read more

I have consistently the worst customer experiences from AUSPOST. I regularly send packages and letters via registered post service, and t...

Winnifred Antoinette Mok

Aus Post's customer chief: CX is about convenience, control and choice

Read more

Such a great new you've shared with us I really agree with the records you shared as this is true that this report may able to quantify t...

Lucy Eva

Report: Mobile app time dominates Australian smartphone usage

Read more

It is heartening to see that the South Pole Group use a Balanced Scorecard to monitor progress. In such a complex area where communicatio...

Clive Keyte

How South Pole Group is tapping media intelligence for customer conversion

Read more

Latest Podcast

More podcasts

Sign in