Unverified50% confidenceFactExact time
贝叶斯方法在20世纪90年代曾被神经网络热潮边缘化，但其理论价值在后来的深度学习不确定性量化中得到重新认可
1
Sources
50%
Confidence
Long-term
Relevance
8/26/2026
First Seen
Sources
Related Entities
Related Claims
Unverified预测性编码理论由神经科学家卡尔·弗里斯顿在赫尔姆霍兹早期感知理论基础上系统化发展69% similarUnverified闭环优化这一思路最早应用于脑机接口领域，后逐渐渗透到感知神经科学研究中69% similarUnverifiedThe phenomenon of catastrophic forgetting was formally described by McCloskey and Cohen in 1989, referring to the tendency of neural networks to overwrite old knowledge when learning new tasks.67% similarUnverified关于计算机辅助证明是否算真正数学证明的哲学争论持续至1990年代才逐渐平息65% similarUnverified大模型时代许多重要发现来自实验先行，有些现象如涌现能力、上下文学习至今没有完美的理论解释65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/802167API
curl https://kongchang.com/api/v1/knowledge/claims/802167MCP
get_claim(id=802167)