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

The real asset of small data – getting granular unearths opportunities

When most marketers use the word ‘data’, what springs to mind are large sets of numbers, Excel spreadsheets, cloud-based IT systems and complicated algorithms. Big data speak is the mot du jour. There is even a big data Week in London called the Festival of Data.

Pip Stocks

CEO and founder, BrandHook

Digital Transformation challenges for CMOs

New problems are rarely fixed by applying old thinking. In the last decade, a combination of circumstances has evolved that requires new thinking from marketers. This new thinking takes advantage of the digital environment and transforms business as we know it.

Mark Cameron

CEO, Working Three

Why innovation requires less certainty and more ambiguity

According to the Knowledge Doubling Theory, the sum total of human knowledge doubles every 12-13 months. With the full evolution of the Internet of Things, it will eventually double every 12 hours. Faced with such a sea of shifting data and knowledge, how can we make progress if we try to nail everything down to a certainty?

Matt Whale

Managing director, How To Impact

Need to improve your customer journey? We're excited to announce that we are holding that we are holding two more sessions of our sellout...

Proto Partners

Customer journeys: The new differentiation battlefield - Customer insights - CMO Australia

Read more

Thanks Mark. A third of customers leave brands after one negative experience, thats why it is ever so important that we optimise EVERY in...

Proto Partners

Customer journeys: The new differentiation battlefield - Customer insights - CMO Australia

Read more

Hi Kyle -- great piece. I couldn't agree with you more when you say that we as marketers are in the business of choice. I actually wrot...

Matthew Willcox

Tapping behavioural science for consumer influence

Read more

Great points. When it comes to optimizing the app experience, making sure you collect rich usage data is important, but making sure you c...

Dustin Amrhein

Why app engagement must be personalised - Mobile strategy - CMO Australia

Read more

You can also use automation to help keep the contact database nice and tidy. For example, programs that check and fix database values (eg...

automatico

3 brands using marketing automation for more than just email

Read more

Latest Podcast

More podcasts

Sign in