In the second week, we learn that in simple logistic regression, the weight matrix w has shape (n_x, 1). This means w has n_x rows and 1 column, so each feature weight is stored in its own row. However, in the third week, second lecture, when we move on to hidden layers, we learn that the new weigh…

It is a very loose standard, but generally a weight matrix size is outputs x inputs.

Well, here is the course convention for “deep neural network classification” (as opposed to “single-layer network doing logistic regression”). I’m continually updating this diagram with observation gleaned from later parts of the course. Hopefully it’s informative. [fwd_prop_two_layer_network]

Problem understanding the shape of w

Course Q&A Deep Learning Specialization Neural Networks and Deep Learning

paulinpaloalto March 29, 2025, 3:22am 3

Here’s a historical thread with some explanation of what is happening when Prof Ng defines the weight matrices in DLS C1 Week 3.

Topic		Replies	Views
Size of W in [9] in C2_W1_Lab02_CoffeeRoasting_TF? Advanced Learning Algorithms week-module-1	5	575	October 19, 2022
[DLS 1] Week 3 Exercise 3 - Weights Matrix shape Neural Networks and Deep Learning coursera-platform	2	500	August 6, 2023
W3_Computing a Neural Network's Output Neural Networks and Deep Learning coursera-platform	1	503	April 10, 2023
Matrix size confusion Neural Networks and Deep Learning week-module-3 , dl-ai-learning-platform	3	13	January 21, 2026
Week 3, Video 3: Understanding matrix size Neural Networks and Deep Learning coursera-platform	7	685	January 29, 2025

Problem understanding the shape of w

Related topics