RT I think there are two main advantages of the positional encoding. First is convenience: you don't have to re-train from scratch when you add data for a new element. Second, it helps with generalization as can be seen for the dissociation of H-F which was not in the training set.


Sign in to participate in the conversation
Mastodon Sorbonne Université

Serveur Mastodon de Sorbonne Université