Week 1, Part 1: The Math You Actually Need
Matrix Multiplication as a Batch of Projections
Given a (sequence_length × d_model) matrix and a (d_model × d_k) weight matrix, state the output shape and explain what each row of the result represents.
Given a (sequence_length × d_model) matrix and a (d_model × d_k) weight matrix, state the output shape and explain what each row of the result represents.