NON-NORMAL RECURRENT NEURAL NETWORK (NNRNN): LEARNING LONG TIME DEPENDENCIES WHILE IMPROVING EXPRESSIVITY WITH TRANSIENT DYNAMICS

von Kerg, Giancarlo
Veröffentlicht in NeurIPS (33. : 2019 : Vancouver, British Columbia) 32nd Conference on Neural Information Processing Systems (NeurIPS 2019) ; Volume 18 of 20 (2020)

UNTANGLING TRADEOFFS BETWEEN RECURRENCE AND SELF-ATTENTION IN ARTIFICIAL NEURAL NETWORKS

von Kerg, Giancarlo
Veröffentlicht in NeurIPS (34. : 2020 : Online) 34th Conference on Neural Information Processing Systems (NeurIPS 2020) ; Volume 24 of 27 (2021)