MXene‐Based Broadband Ultrafast Nonlinear Activator for Optical Computing

• DOI: 10.1002/adom.202200714
• Publication Date: 2022-06-14T14:49:57Z
• Authors: Zhan Yang; Weimin Tan; Tianju Zhang; Chenduan Chen; Zixin Wang; Yu Mao; Chenxi Ma; Qing Lin; Wanjun Bi; Fei Yu; Bo Yan; Jun Wang
• Keywords: Reconfigurability; Linearity

Abstract Optical neural networks (ONNs) are particularly advantageous owing to their inherent parallelism and low energy consumption. However, one of the obstacles implementation ONNs is lack optical nonlinearity. In this study, nonlinear activators for prepared by combining Ti 3 C 2 T x MXene with microfibers principles verified. Activation functions obtained from experimental measurements used simulate multiclassification super‐resolution reconstruction tasks performance comparable that activation commonly in computers. Four necessary criteria proposed validated evaluating activator: recovery time, deviation linearity, function close identity mapping, reconfigurability configuration. Theoretically, activator can compute 100 times faster than electronic computers be as a unit help integration artificial intelligence.