Multi-Head Attention

One attention pattern can only track one relationship, so transformers run several heads in parallel, each with its own Q/K/V projection. Watch the same word get routed to the verb by one head and to a similar word by another, then concatenated. The 'multi-head' in every transformer.

🎬 Free preview in EN / हिं / ES — watch it, then unlock the lab to try it yourself.

54 deep, interactive Pro labs like this one — drag the knobs, watch the math move.
The entire course catalog — AI, ML, LLMs, DevOps, security & system design.
The full video library in EN / हिं / ES, plus verifiable certificates.

Start 30 days free → Try 34 free labs No card needed · cancel anytime Already Pro? Log in