Unverified60% confidenceFactExact time
The Transformer is a deep learning architecture proposed by Google in 2017 in the paper "Attention Is All You Need".
2
Sources
60%
Confidence
Long-term
Relevance
8/23/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAlexNet在2012年引发深度学习革命，Transformer架构前身的注意力机制论文于2017年首发于顶级会议74% similarUnverified"Deep Learning" (the "Flower Book") was written in 2016, prior to the publication of the Transformer architecture.71% similarUnverifiedSpeculative decoding technology was first systematically proposed by Google DeepMind in the paper "Fast Inference from Transformers via Speculative Decoding".65% similarUnverified"Understanding Deep Learning" was published by Simon Prince in 2023, is freely available, and covers modern architectures such as Transformers and diffusion models.63% similarUnverifiedCurrent mainstream deep learning architectures (including Transformers and convolutional neural networks) inherit the core assumptions of the information-processing paradigm: information can be encoded as numerical vectors, hierarchically transformed, and read from or written to explicit locations.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/789966API
curl https://kongchang.com/api/v1/knowledge/claims/789966MCP
get_claim(id=789966)