What Happens When You Give an AI a Working Memory?

 

 

google-deepmind

By Will Knight


A new kind of computer, devised by researchers at Google DeepMind in the U.K., could broaden the abilities of today’s best AI systems by giving them an important new feature—a kind of working memory.

The researchers show that the computer, which consists of a large neural network connected to a unique form of memory, can perform relatively complex tasks by figuring out for itself what information to hold in its memory. The tasks include figuring out the best way to get from one station to another on London’s spaghetti-like Underground transit network, after exploring diagrams of other types of networks and learning about the most salient features.

Read the full article on MIT Technology Review Here

Post Your Thoughts

Related Posts
Jeff Bezos talks business principles, AI and machine learning, plus space

Jeff Bezos talks business principles, AI and machine learning, plus space

By Tian DuBelko     Amazon CEO Jeff Bezos stopped by the annual Internet Association…

Apple turns to the “dark side” of data

Apple turns to the “dark side” of data

By Tian DuBelko Apple is turning to the dark side of data with its latest…

Google Diversity Initiative Gets Slow Start

Google Diversity Initiative Gets Slow Start

  By Deborah M. Todd Alphabet’s Google on Thursday released data on its two-year-old initiative…

Close

Book a Tour

Would you like to see our space before joining? Come and visit our coworking space. Please fill out the form and our manager will get back asap.