Alphabet's DeepMind AI learns to 'remember' previous knowledge

Alphabet's DeepMind AI learns to 'remember' previous knowledge

PanARMENIAN.Net - For all the talk of artificial intelligence becoming increasingly brain-like, there's one area where it frequently falls short: memory. Neural networks usually have to learn everything they need to know about their duties, rather than building on top of existing experiences like real brains do. Alphabet's DeepMind team hopes to fix that. They've crafted an algorithm that lets a neural network 'remember' past knowledge and learn more effectively. The approach is similar to how your own mind works, and might even provide insights into the functioning of human minds, Engadget reports.

Much like real synapses, which tend to preserve connections between neurons when they've been useful in the past, the algorithm (known as Elastic Weight Consideration) decides how important a given connection is to its associated task. Ask the neural network to learn a new task and the algorithm will safeguard the most valuable connections, linking them to new tasks when relevant. In tests with 10 classic Atari video games, the AI didn't need learn how to play each game in isolation. It could learn them sequentially, taking the knowledge accrued in one game and applying it to the other.

The technology is more than a little rough around the edges. It's a jack of all trades, but a master of none. A single-task neural network is still better when limited to one game, DeepMind's James Kirkpatrick says to Wired. It's also not ready to adapt to situations on the spot. The algorithm shows that it's at least possible to give AI memory-like functions, however.

 Top stories
Gurgen Khachatryan claimed that the "illegalities have been taking place in 2020."
The care reaction is slated to launch globally on Facebook’s app and website sometime next week.
The Yesayan brothers had earlier offered AMD 22,1 billion for the shares they do not control.
Playrix Armenia is already on its way to becoming the largest gaming company in the region," said co-founder of Playrix.
Partner news
---