Thank you for this excellent work, open sourcing the code, and the accessible write-ups. Did you by any chance already evaluate the model under sequential task learning? I'd like to know if this model has any appreciable impact (positive or negative) on learning interference / catastrophic forgetting.
Thank you for this excellent work, open sourcing the code, and the accessible write-ups. Did you by any chance already evaluate the model under sequential task learning? I'd like to know if this model has any appreciable impact (positive or negative) on learning interference / catastrophic forgetting.