Neural Network Programming with TensorFlow

Matrix multiplication

Matrix multiplication of matrices A and B is a third matrix, C:

C = AB

The element-wise product of matrices is called a Hadamard product and is denoted as A.B.

The dot product of two vectors x and y of the same dimensionality is the matrix product x transposing y. Matrix product C = AB is like computing C_i,j as the dot product between row i of matrix A and column j of matrix B:

The following example shows the Hadamard product and dot product using tensor objects:

import tensorflow as tf mat1 = tf.constant([[4, 5, 6],[3,2,1]])mat2 = tf.constant([[7, 8, 9],[10, 11, 12]]) # hadamard product (element wise)mult = tf.multiply(mat1, ...