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

Why 2017 will herald a resurgence of values-based marketing

It doesn’t take long for predictions to become predictable: The rise and rise of Facebook; advancements in analytics; the normalisation of chatbots; personalisation, programmatic, automation, authenticity… The prediction that’s missing from these lists is that in 2017 we will witness a resurgence of values-based marketing.

Jacqueline Burns

Founder, Market Expertise

Why customer experience driven growth is set to take off

Our overall brand perceptions are invariably shaped by our experiences. And loyal customer relationships can be severed in moments by a negative service interaction.

Consistency and conversation: How branding and advertising can work better together

Advertising and branding are two of the most visible outputs of marketing, which is why getting them right is so important. However, too often the line between branding and advertising becomes blurred. This means advertising activity can be out of sync with brand, resulting in poor results for both functions.

Dan Ratner

managing director, uberbrand

Someone needs a swift kick up the bum for such an idiotic idea.

random

​Why a degree is no longer enough to get you hired as a skilled marketer

Read more

The frequent flyer programs are the new profit machines for airlines all over the world, as they have morphed to be mass marketing machin...

Steve@iFLYflat

Velocity frequent flyers program strong performer in mixed half-year for Virgin

Read more

Hi Jennifer, thanks for sharing these info regarding the digital marketing trends.I've created a related video to this topic, would you m...

Fabio Carry

Predictions: 17 digital marketing trends for 2017

Read more

Great news. Marketing automation can be very useful for companies at various stages of development. With so many tools out there it's bet...

Ben

How HBF rolled out marketing automation in eight months

Read more

I read a report that the business sector in Australia as a whole have yet to fully harness and see the proactive change that predictive a...

Alex Martin

Report: Predictive analytics, IoT, machine learning battle it out for marketing dollars

Read more

Latest Podcast

More podcasts

Sign in