Unverified90% confidenceFactTime unknown
Hinton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
1
Sources
90%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
AI预测中的"方向性准确"：为什么比精确预测更有价值
twitterlevelsio
Related Entities
Related Claims
Unverified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72% similarUnverified链式法则系统应用于神经网络训练直到1986年Rumelhart、Hinton和Williams的论文才被深度学习领域广泛认知67% similarUnverified2006年Geoffrey Hinton提出深度信念网络的逐层预训练方法66% similarUnverifiedA mature discovery layer considers at least three signals: current learning path, recent activity, and intent behind the question64% similarUnverified信息瓶颈框架最初由Tishby与Pereira在1999年提出，Tishby与Schwartz-Ziv在2017年将其引入深度学习61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/7305API
curl https://kongchang.com/api/v1/knowledge/claims/7305MCP
get_claim(id=7305)