Unverified50% confidenceFactExact time
In 1986, David Rumelhart, Geoffrey Hinton, and Ronald Williams published a landmark paper on the backpropagation algorithm, demonstrating that multi-layer networks can be effectively trained via gradient descent.
1
Sources
50%
Confidence
Long-term
Relevance
8/16/2026
First Seen
Sources
用VRML可视化MLP：XOR问题的3D神经网络演示
Related Claims
VerifiedThe backpropagation algorithm was popularized by Rumelhart, Hinton, and Williams in their 1986 paper, with the chain rule as its mathematical core.79% similarUnverified约束传播的思想最早可追溯至1970年代阿兰·马克沃斯对弧一致性算法的研究60% similarVerifiedResidual connections were originally proposed by He et al. in the 2015 ResNet paper to address the vanishing gradient problem in deep neural networks.60% similarUnverified反向传播算法此前曾被多人独立发现，Paul Werbos于1974年博士论文中已有类似推导，Yann LeCun在1985年论文中提出等价思路59% similarUnverified有限状态机的理论基础由沃伦·麦卡洛克和沃尔特·皮茨在1943年的神经网络研究中奠定，后经摩尔和米利在20世纪50年代形式化为完整的自动机理论56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/756911API
curl https://kongchang.com/api/v1/knowledge/claims/756911MCP
get_claim(id=756911)