Lian Minrui, Gao Changsong, Lin Zhenyuan, Shan Liuting, Chen Cong, Zou Yi, Cheng Enping, Liu Changfei, Guo Tailiang, Chen Wei, Chen Huipeng
Institute of Optoelectronic Display, National & Local United Engineering Lab of Flat Panel Display Technology, Fuzhou University, Fuzhou, 350002, China.
Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China, Fuzhou, 350100, China.
Light Sci Appl. 2024 Aug 1;13(1):179. doi: 10.1038/s41377-024-01516-z.
Memristor-based physical reservoir computing holds significant potential for efficiently processing complex spatiotemporal data, which is crucial for advancing artificial intelligence. However, owing to the single physical node mapping characteristic of traditional memristor reservoir computing, it inevitably induces high repeatability of eigenvalues to a certain extent and significantly limits the efficiency and performance of memristor-based reservoir computing for complex tasks. Hence, this work firstly reports an artificial light-emitting synaptic (LES) device with dual photoelectric output for reservoir computing, and a reservoir system with mixed physical nodes is proposed. The system effectively transforms the input signal into two eigenvalue outputs using a mixed physical node reservoir comprising distinct physical quantities, namely optical output with nonlinear optical effects and electrical output with memory characteristics. Unlike previously reported memristor-based reservoir systems, which pursue rich reservoir states in one physical dimension, our mixed physical node reservoir system can obtain reservoir states in two physical dimensions with one input without increasing the number and types of devices. The recognition rate of the artificial light-emitting synaptic reservoir system can achieve 97.22% in MNIST recognition. Furthermore, the recognition task of multichannel images can be realized through the nonlinear mapping of the photoelectric dual reservoir, resulting in a recognition accuracy of 99.25%. The mixed physical node reservoir computing proposed in this work is promising for implementing the development of photoelectric mixed neural networks and material-algorithm collaborative design.
基于忆阻器的物理储层计算在高效处理复杂的时空数据方面具有巨大潜力，这对推动人工智能发展至关重要。然而，由于传统忆阻器储层计算的单物理节点映射特性，它不可避免地在一定程度上导致特征值的高重复性，并显著限制了基于忆阻器的储层计算处理复杂任务的效率和性能。因此，这项工作首先报道了一种用于储层计算的具有双光电输出的人工发光突触（LES）器件，并提出了一种具有混合物理节点的储层系统。该系统使用由不同物理量组成的混合物理节点储层，即具有非线性光学效应的光输出和具有记忆特性的电输出，有效地将输入信号转换为两个特征值输出。与先前报道的基于忆阻器的储层系统不同，后者在一个物理维度上追求丰富的储层状态，我们的混合物理节点储层系统可以在不增加器件数量和类型的情况下，通过一次输入在两个物理维度上获得储层状态。人工发光突触储层系统在MNIST识别中的识别率可达97.22%。此外，通过光电双储层的非线性映射可实现多通道图像的识别任务，识别准确率达99.25%。这项工作中提出的混合物理节点储层计算在实现光电混合神经网络的发展和材料 - 算法协同设计方面具有广阔前景。
