Memorize or generalize? Searching for a compositional RNN in a haystack
arXiv: Artificial Intelligence, Volume abs/1802.06467, 2018.
Neural networks are very powerful learning systems, but they do not readily generalize from one task to the other. This is partly due to the fact that they do not learn in a compositional way, that is, by discovering skills that are shared by different tasks, and recombining them to solve new problems. In this paper, we explore the compos...More
Full Text (Upload PDF)
PPT (Upload PPT)