Scholarlink

<p>In the field of neuromorphic computing, time-series prediction poses a significant challenge to recurrent neural network architectures, often requiring task-specific customization that limits the development of general-purpose computing platforms. In this work, we implement a physical echo-state network (ESN) using ambipolar organic–inorganic heterostructure transistors to form its reservoir layer. Leveraging the ambipolar nature of the transistor, its variable-resistance region enables sparse matrix operations, while the saturation region provides tanh-like nonlinearity, making it well-suited for implementing both synaptic weighting and neuronal activation in an ESN. Additionally, its dynamic response naturally introduces temporal attributes. Thus, it can serve as a neuromorphic computing model for time-series tasks. Without the involvement of dynamic mechanisms, it is capable of performing image recognition, time-series prediction, and multimodal recognition tasks. When dynamic mechanisms are incorporated, the model achieves an accuracy of 96.98% on the MNIST handwritten digit dataset and 86.67% on the Fashion-MNIST dataset. This work offers a neuromorphic computing architecture, providing insights for tasks such as nonlinear mapping and time-series prediction.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Physical echo state network based on the nonlinearity and dynamic response of ambipolar heterostructure transistors

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月28日

查看全文
  • Wen-Min Zhong,
  • Wenbin Zhang,
  • Yu-Xiang Zeng,
  • JiYu Zhao,
  • Ziqi Jia,
  • Guanglong Ding,
  • Su-Ting Han,
  • Vellaisamy A. L. Roy,
  • Ye Zhou

摘要

In the field of neuromorphic computing, time-series prediction poses a significant challenge to recurrent neural network architectures, often requiring task-specific customization that limits the development of general-purpose computing platforms. In this work, we implement a physical echo-state network (ESN) using ambipolar organic–inorganic heterostructure transistors to form its reservoir layer. Leveraging the ambipolar nature of the transistor, its variable-resistance region enables sparse matrix operations, while the saturation region provides tanh-like nonlinearity, making it well-suited for implementing both synaptic weighting and neuronal activation in an ESN. Additionally, its dynamic response naturally introduces temporal attributes. Thus, it can serve as a neuromorphic computing model for time-series tasks. Without the involvement of dynamic mechanisms, it is capable of performing image recognition, time-series prediction, and multimodal recognition tasks. When dynamic mechanisms are incorporated, the model achieves an accuracy of 96.98% on the MNIST handwritten digit dataset and 86.67% on the Fashion-MNIST dataset. This work offers a neuromorphic computing architecture, providing insights for tasks such as nonlinear mapping and time-series prediction.