Inspires effective alternatives to backpropagation:predictive coding helps understand and build learning
Zhenghua Xu1
Miao Yu2
Yuhang Song3
1.School of Health Sciences and Biomedical Engineering,Hebei University of Technology,Tianjin,China;Department of Computer Science,University of Oxford,Oxford,UK2.School of Health Sciences and Biomedical Engineering,Hebei University of Technology,Tianjin,China3.Department of Computer Science,University of Oxford,Oxford,UK
摘要：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.
机标关键词：learningbuildalternativesbackpropagationcodingeffectivehelpsinspires
论文发表日期：2025-11-27
在线出版日期：2025-08-15（本平台首次上网日期，不代表文献的发表时间）
页数：2( 3215-3216 )