When vectorizing calculation for neural networks for entire set of m samples, X is mentioned as an (n, m) matrix. The equation for calculation of Z is Z = transpose(W) * X + B where W is (m, 1) matrix, transpose(W) will be (1, m). So, shouldn’t X be (m, n) matrix. Otherwise, matrix multiplication …

Shouldn't X be (m,n) matrix when vectorizing neural network

Rashmi March 5, 2022, 8:28am 2

Hi @Gaurav_Malhotra, here’s a thread to clarify your query. Thanks.

1 Like

Topic		Replies	Views
Is W[1] the transposed version on W Neural Networks and Deep Learning	1	505	June 2, 2022
Gradient Descent on m Examples - Neural Networks Basics \| Coursera Neural Networks and Deep Learning	7	589	January 18, 2022
Matrix multiplication in neural network Advanced Learning Algorithms week-1	2	49	August 30, 2024
WEEK 2 : Confusion about the matrix created from input data Neural Networks and Deep Learning	5	461	May 31, 2023
Matrix multiplication lecture clarification - NN - Why do we transpose at all Advanced Learning Algorithms week-1	1	347	September 17, 2023