Conceptos Básicos
Kontinuierliches Lernen in künstlichen neuronalen Netzwerken ist durch katastrophales Vergessen eine Herausforderung.
Estadísticas
Artificial neural networks tend to rapidly and drastically forget previously learned information when learning something new.
Deep learning methods for continual learning are evaluated using metrics covering performance, diagnostic analysis, and resource efficiency.
Citas
"Catastrophic forgetting is the phenomenon that artificial neural networks tend to rapidly and drastically forget previously learned information when learning new information."
"An important reason for the inability of deep neural networks to continually learn is catastrophic forgetting."