Nonlinear germanium-silicon photodiode for activation and monitoring in photonic neuromorphic networks
Top Cited Papers
Open Access
- 13 October 2022
- journal article
- research article
- Published by Springer Nature in Nature Communications
- Vol. 13 (1) , 1-9
Abstract
Silicon photonics is promising for artificial neural networks computing owing to its superior interconnect bandwidth, low energy consumption and scalable fabrication. However, the lack of silicon-integrated and monitorable optical neurons limits its revolution in large-scale artificial neural networks. Here, we highlight nonlinear germanium-silicon photodiodes to construct on-chip optical neurons and a self-monitored all-optical neural network. With specifically engineered optical-to-optical and optical-to-electrical responses, the proposed neuron merges the all-optical activation and non-intrusive monitoring functions in a compact footprint of 4.3 × 8 μm2. Experimentally, a scalable three-layer photonic neural network enables in situ training and learning in object classification and semantic segmentation tasks. The performance of this neuron implemented in a deep-scale neural network is further confirmed via handwriting recognition, achieving a high accuracy of 97.3%. We believe this work will enable future large-scale photonic intelligent processors with more functionalities but simplified architecture.Keywords
This publication has 56 references indexed in Scilit:
- Non-Invasive On-Chip Light Observation by Contactless Waveguide Conductivity MonitoringIEEE Journal of Selected Topics in Quantum Electronics, 2014
- Artificial neural networks in medical diagnosisJournal of Applied Biomedicine, 2013
- Response surface optimization and artificial neural network modeling of microwave assisted natural dye extraction from pomegranate rindIndustrial Crops and Products, 2012
- How Important is Working with an Ordered Electrode to Improve the Charge Collection Efficiency in Nanostructured Solar Cells?The Journal of Physical Chemistry Letters, 2012
- Measurement and modeling of infrared nonlinear absorption coefficients and laser-induced damage thresholds in Ge and GaSbJournal of the Optical Society of America B, 2010
- Germanium: From its discovery to SiGe devicesMaterials Science in Semiconductor Processing, 2006
- Novel naphthylstyryl-pyridinium potentiometric dyes offer advantages for neural network analysisJournal of Neuroscience Methods, 2004
- Variable optical attenuator based on thermally tuned Mach–Zehnder interferometer within a twin core fiberOptics Communications, 2004
- Back-propagation neural networks for modeling complex systemsArtificial Intelligence in Engineering, 1995
- Experimental realization of any discrete unitary operatorPhysical Review Letters, 1994