Intersubband engineered nonlinear activation function for photonic neural networks
Fast, sensitive, and compact photonic nonlinear activation devices are crucial for forming photonic neural networks with high computational efficiency. However, conventional photonic activation units lack suitable nonlinearity due to weak optical nonlinearities. Using intersubband nanostructures, we introduce the smallest possible optoelectronic approach for nonlinear processing in photonic neural networks. Here we also demonstrate the simulation and fabrication of the intersubband nanostructures. The simulation results shows a 3.5 microwatt threshold and an optical response time of 10 picoseconds within a device that is only 4 microns in length.
Authors
- Zheheng Xu (ORCID: https://orcid.org/0000-0003-0300-2928)
- Sadhvikas Addamane (ORCID: https://orcid.org/0000-0003-2958-3767)
- David Burghoff (ORCID: https://orcid.org/0000-0001-5848-2389)
Institutions
- The University of Texas at Austin (US)
Publication Details
- Published
- 2024-10-02
- DOI
- https://doi.org/10.1117/12.3027777
- Primary Topic
- Neural Networks and Reservoir Computing
- Type
- article
- Field-Weighted Citation Impact
- 0.00