one-hot里“star”和“sun”相似度直接是0，分布式表示才让语义相近的词在向量空间里聚在一起。
This is a dev post classified by Jev as Other (a tutorial), kept by the Dev Radar because it carries real work, not commentary.
🔥智普创始人唐杰清华课堂上把词向量讲透！ one-hot里“star”和“sun”相似度直接是0，分布式表示才让语义相近的词在向量空间里聚在一起。 CBOW用上下文预测中心词，Skip-gram反过来用中心词预测上下文，CBOW更快还一样能打。 从token到稠密向量，这才是大模型真正起步的地方。 #唐杰 #清华大学 #词向量 #CBOW #SkipGram #Word2Vec #机器学习 #大模型基座 #智谱AI #NLP基础
Posted by SuSu_酥酥👅 (16.8k followers) 1 h ago · 14 likes · 1.1k views · view the original post on X. Kept by the Dev Radar as Other.
More dev work like this
- AI 炒股别只会问一句“这只票能不能买”。 — @bkdgiffug
- 做闲鱼电子资料、卡密类商品的，可以看看这个开源项目 Ydisks-Xianyu-Helper。 — @bkdgiffug
- Opus 5.5 changes everything. — @Everlier
- Here are some examples of the difference steps makes for image generation using… — @ItsmeAjayKV
- Stop searching for a Granola or a Wispr Flow alternative — @FluidVoiceApp
- Our Opus 5.5 benchmarking versus Fable 5.1: — @PatrickMoorhead
- Meet Occamy 1.0 APEX I MiniPlus V2.1 Abliterated GGUF. A custom quantized text… — @HuggingModels
- Our friend @spedemo has made a real Marvin, 3D printed, remote controlled, with voice… — @ashtom
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 23k posts from 5k X accounts over the last 21 days, 2.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-24 00:15 UTC. Full method.