Unverified50% confidenceOpinionExact time
The idea of distributed representations—whereby a concept is encoded by multiple neurons jointly rather than stored in a single node—is the theoretical predecessor of representation learning in modern word vectors and large language models.
1
Sources
50%
Confidence
Long-term
Relevance
10/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSymbolic systems use discrete, composable symbols to represent concepts and relationships, whereas neural networks rely on distributed patterns in continuous vector spaces.72% similarUnverifiedNeural networks are more like something that is 'grown' rather than 'designed,' fine-tuned from a random state by providing data and learning algorithms.71% similarUnverified向量嵌入的核心思想源于分布式语义假说，即语义相近的词或句子在向量空间中距离更近70% similarUnverifiedThe facts absorbed by large language models during the pre-training phase are encoded in a distributed manner across billions of parameters, with a single fact diffused across the activation patterns of hundreds or even thousands of neurons69% similarUnverified嵌入思想源自2013年Word2Vec提出的分布式语义假说，即词的含义由其上下文分布决定69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/991727API
curl https://kongchang.com/api/v1/knowledge/claims/991727MCP
get_claim(id=991727)