中国神经再生研究(英文版) ›› 2025, Vol. 20 ›› Issue (11): 3215-3216.doi: 10.4103/NRR.NRR-D-24-00629

• 观点:神经损伤修复保护与再生 • 上一篇    下一篇

启发反向传播的有效替代方案:预测编码有助于理解和构建学习

  

  • 出版日期:2025-11-15 发布日期:2025-02-23

Inspires effective alternatives to backpropagation: predictive coding helps understand and build learning

Zhenghua Xu*, #, Miao Yu# , Yuhang Song   

  1. School of Health Sciences and Biomedical Engineering, Hebei University of Technology, Tianjin, China (Xu Z, Yu M) Department of Computer Science, University of Oxford, Oxford, UK (Xu Z, Song Y)
  • Online:2025-11-15 Published:2025-02-23
  • Contact: Zhenghua Xu, PhD, xuzhenghua1987@gmail.com.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China, No. 62276089.

摘要: https://orcid.org/0000-0002-6719-7333 (Zhenghua Xu)

Abstract: Artificial neural networks are capable of machine learning by simulating the hierarchical structure of the human brain. To enable learning by brain and machine, it is essential to accurately identify and correct the prediction errors, referred to as credit assignment (Lillicrap et al., 2020). It is critical to develop artificial intelligence by understanding how the brain deals with credit assignment in neuroscience.