Get the latest tech news
Selective Forgetting Can Help AI Learn Better
Erasing key information during training allows machine learning models to learn new languages faster and more easily.
The new research marks “a significant advance in the field,” said Jea Kwon, an AI engineer at the Institute for Basic Science in South Korea. A few years ago, Artetxe and others trained a neural network in one language, then erased what it knew about the building blocks of words, called tokens. While this forgetting approach was an effective way to add a new language to an already trained model, the retraining was still demanding—it required a lot of linguistic data and processing power.
Or read this on Wired