Unverified50% confidenceFactExact time
The systematic application of the chain rule to neural network training was not widely recognized in the deep learning field until Rumelhart, Hinton, and Williams' 1986 paper.
1
Sources
50%
Confidence
Long-term
Relevance
7/19/2026
First Seen
Sources
梯度下降与反向传播详解：神经网络学习机制从零拆解
Related Claims
VerifiedRumelhart, Hinton, and Williams published the paper 'Learning representations by back-propagating errors' in Nature in 1986, bringing backpropagation to widespread recognition in the deep learning field.73% similarUnverifiedHinton等人在深度学习取得突破之前已经在'神经网络寒冬'中坚持研究长达数十年67% similarUnverified2020年OpenAI的Kaplan等人论文首次系统证明神经网络性能与模型参数量、训练数据量、计算量之间存在幂律关系66% similarUnverified深度学习先驱Hinton、LeCun、Bengio在神经网络被主流AI学界视为死路的二十年间持续坚持66% similarUnverifiedThis deep learning introductory tutorial on Bilibili claims to be the 'most comprehensive neural network course,' covering everything from the mathematical principles of neural networks to TensorFlow framework applications to hands-on image recognition, with a three-day cycle.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/556684API
curl https://kongchang.com/api/v1/knowledge/claims/556684MCP
get_claim(id=556684)