Shelley Fan in Singularity Hub:
Humans are exceptionally good at transferring old skills to new problems. Machines, despite all their recent wins against humans, aren’t. This is partly due to how they’re trained: artificial neural networks like Google’s DeepMind learn to master a singular task and call it quits. To learn a new task, it has to reset, wiping out previous memories and starting again from scratch.
This phenomenon, quite aptly dubbed “catastrophic forgetting,” condemns our AIs to be one-trick ponies.
Now, taking inspiration from the hippocampus, our brain’s memory storage system, researchers at DeepMind and Imperial College London developed an algorithm that allows a program to learn one task after another, using the knowledge it gained along the way.
When challenged with a slew of Atari games, the neural network flexibly adapted its strategy and mastered each game, while conventional, memory-less algorithms faltered.
More here. [Thanks to Ali Minai.]