Modern Hopfield Networks and Attention for Immune Repertoire Classification
Michael Widrich, Bernhard Schäfl, Milena Pavlović, Hubert Ramsauer, Lukas Gruber, Markus Holzleitner, J. Brandstetter, Geir Kjetil Sandve, Victor Greiff, Sepp Hochreiter, Günter Klambauer
Transformer attention is recast as the update rule of modern Hopfield networks, and the resulting DeepRC classifier handles immune repertoires with enormous instance counts and few informative sequences.
bioRxiv · Apr 12, 2020 · PreprintBioinformatics