Are Deep Neural Architectures Losing Information? Invertibility is Indispensable

Yang Liu, Zhenyue Qin, Saeed Anwar, Sabrina B. Caldwell, Tom Gedeon. Are Deep Neural Architectures Losing Information? Invertibility is Indispensable. In Haiqin Yang, Kitsuchart Pasupa, Andrew Chi-Sing Leung, James T. Kwok, Jonathan H. Chan, Irwin King, editors, Neural Information Processing - 27th International Conference, ICONIP 2020, Bangkok, Thailand, November 23-27, 2020, Proceedings, Part III. Volume 12534 of Lecture Notes in Computer Science, pages 172-184, Springer, 2020. [doi]

Abstract

Abstract is missing.