catastrophic forgetting

AI has the potential to learn like humans

An algorithm that teaches machines to learn without human supervision

Artificial neural networks are computing systems inspired by biological neural networks that constitute animal brains. Like biological models, they can learn (be trained) by processing examples and forming probability associations, then apply that information to other tasks.

Do artificial neural networks need “sleep” in order to do better?

Solved: A major long-standing obstacle to increasing AI capabilities has been “catastrophic forgetting”