Unverified50% confidenceFactExact time
LeNet-5模型由Yann LeCun在1998年提出，用于手写数字识别，奠定了卷积神经网络的基础
1
Sources
50%
Confidence
Long-term
Relevance
8/23/2026
First Seen
Sources
Related Entities
Related Claims
Unverified1998年Yann LeCun提出的LeNet-5是CNN的经典原型80% similarUnverifiedCNN（卷积神经网络）最早由Yann LeCun在1998年用于手写数字识别72% similarUnverified基于追踪的JIT编译技术最早可追溯到2000年代初期Dynamo项目的研究成果，后被Mozilla的TraceMonkey和Adobe的Tamarin-Tracing引擎采用53% similarUnverified2017年Google的Tacotron和DeepMind的WaveNet是端到端神经网络语音合成的里程碑52% similarUnverifiedThe Transformer architecture was introduced in 2017 and is foundational to large language models such as ChatGPT, Claude, DeepSeek, and ERNIE Bot51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/788631API
curl https://kongchang.com/api/v1/knowledge/claims/788631MCP
get_claim(id=788631)