АДАПТИВНА РЕГУЛЯРИЗАЦІЯ ЗНАНЬ ДЛЯ ТРАНСФОРМЕРНИХ АРХІТЕКТУР У ЗАДАЧАХ ПОСЛІДОВНОГО НАВЧАННЯ
The subject matter of the article is development of latent representation regularization mechanism in transformer-based architecture under conditions of continuous learning with domain shifts. Modern language models achieve high quality in static learning scenarios, but they remain limited in long-term operation cases,...