How are vectors and matrices are multiplied in supervised machine learning?

I maintained the "supervised" in the title

Link

edited Feb 11, 2019 at 21:22

DukeZhou

6.2k
5
27
54

How are vectors and matrices are multiplied in deepsupervised machine learning?

A few improvements

Source Link

edit approved Feb 11, 2019 at 21:22

nbro

41.4k
12
114
205

Understand the way vertex How are vectors and matrices are multiplied in deep learning suprivised parametric learning?

I’veI've recently started reading a book about deep learning (machine learning). The book is titled “grokking"Grokking Deep Learning” byLearning" (by Andrew W Trask). The areas of confusing isIn chapter 3 pages(pages 44 and 45. It), it talks about multiplying vectors using dot product and elementwiseelement-wise multiplication. For instance, taking 3 scalar inputs (vector) and 3 vector weights (vectormatrix) and multiplying.

From my understanding, when multiplying vectors the size needs to be identical. The concept I’mI have a hard time understanding is multiplying vectors by a matrix. The book gives an example of an 1x4(vector) vector being multipledmultiplied by 4x3(matrix) matrix. The output is an 1x3 vector. ImI'm am confused because I assumed multiplying vector by matrix needs the same number of columns as well, but I have read that the matrixesmatrices need rows equal to the vectors columns.

This is confusing to me because ifIf I do not have an equal number of columns, how does my deep learning algorithm multiply each input in my vector by a corresponding weight?

Understand the way vertex and matrices are multiplied in deep learning suprivised parametric learning

I’ve recently started reading a book about deep learning (machine learning). The book is titled “grokking Deep Learning” by Andrew W Trask. The areas of confusing is chapter 3 pages 44 and 45. It talks about multiplying vectors using dot product and elementwise multiplication. For instance, taking 3 inputs(vector) and 3 weights(vector) and multiplying.

From my understanding, when multiplying vectors the size needs to be identical. The concept I’m have hard time understanding is multiplying vectors by a matrix. The book gives an example of an 1x4(vector) being multipled by 4x3(matrix). The output is an 1x3 vector. Im am confused because I assumed multiplying vector by matrix needs the same number of columns as well but have read that the matrixes need rows equal to the vectors columns.

This is confusing to me because if I do not have equal number of columns how does my deep learning algorithm multiply each input in my vector by a corresponding weight?

How are vectors and matrices are multiplied in deep learning?

I've recently started reading a book about deep learning. The book is titled "Grokking Deep Learning" (by Andrew W Trask). In chapter 3 (pages 44 and 45), it talks about multiplying vectors using dot product and element-wise multiplication. For instance, taking 3 scalar inputs (vector) and 3 vector weights (matrix) and multiplying.

From my understanding, when multiplying vectors the size needs to be identical. The concept I have a hard time understanding is multiplying vectors by a matrix. The book gives an example of an 1x4 vector being multiplied by 4x3 matrix. The output is an 1x3 vector. I'm am confused because I assumed multiplying vector by matrix needs the same number of columns, but I have read that the matrices need rows equal to the vectors columns.

If I do not have an equal number of columns, how does my deep learning algorithm multiply each input in my vector by a corresponding weight?