All-analog photoelectronic chip for high-speed vision tasks.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 37880362.
- Also identified by DOI 10.1038/s41586-023-06558-8 and PMC identifier 10620079.
- Licence recorded as CC BY.
- The licence permits redistribution, so the abstract is shown in full and the full text is available from the publisher.
Abstract
Photonic computing enables faster and more energy-efficient processing of vision data<sup>1-5</sup>. However, experimental superiority of deployable systems remains a challenge because of complicated optical nonlinearities, considerable power consumption of analog-to-digital converters (ADCs) for downstream digital processing and vulnerability to noises and system errors<sup>1,6-8</sup>. Here we propose an all-analog chip combining electronic and light computing (ACCEL). It has a systemic energy efficiency of 74.8 peta-operations per second per watt and a computing speed of 4.6 peta-operations per second (more than 99% implemented by optics), corresponding to more than three and one order of magnitude higher than state-of-the-art computing processors, respectively. After applying diffractive optical computing as an optical encoder for feature extraction, the light-induced photocurrents are directly used for further calculation in an integrated analog computing chip without the requirement of analog-to-digital converters, leading to a low computing latency of 72 ns for each frame. With joint optimizations of optoelectronic computing and adaptive training, ACCEL achieves competitive classification accuracies of 85.5%, 82.0% and 92.6%, respectively, for Fashion-MNIST, 3-class ImageNet classification and time-lapse video recognition task experimentally, while showing superior system robustness in low-light conditions (0.14 fJ μm<sup>-2</sup> each frame). ACCEL can be used across a broad range of applications such as wearable devices, autonomous driving and industrial inspections.