Google's DeepMind comes up with way to add memory to AI

Google's DeepMind AI researchers came up with a new algorithm that allows artificial intelligence to learn, retain the information, and use it again in a new situation. Previously, DeepMind created trained an AI agent that mastered a game like Space Invaders, but it could only learn to play one game. With the new algorithm, the AI agent can use the knowledge gained from mastering one game to master another one. Basically, it mimics continual learning:

"The ability to learn tasks in succession without forgetting is a core component of biological and artificial intelligence," the computer scientists write in the paper. Kirkpatrick says a "significant shortcoming" in neural networks and artificial intelligence has been its inability to transfer what it has learned from one task to the next.

The group says it has been able to show "continual learning" that's based on 'synaptic consolidation'. In the human brain, the process is described as "the basis of learning and memory".

Full details at Wired.