# Week 3: matrix W **URL:** \ **Category:** Neural Networks and Deep Learning\ **Tags:** coursera-platform\ **Created:** [August 15, 2021, 12:13am UTC](https://community.deeplearning.ai/t/week-3-matrix-w/28914 "2021-08-15T00:13:15Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![echerny](https://avatars.discourse-cdn.com/v4/letter/e/ea666f/32.png) [@echerny](https://community.deeplearning.ai/u/echerny)\ **Post date:** [August 15, 2021, 12:13am UTC](https://community.deeplearning.ai/t/week-3-matrix-w/28914/1 "2021-08-15T00:13:15Z")
![Screen Shot 2021-08-14 at 5.06.03 PM](https://global.discourse-cdn.com/dlai/original/2X/3/324919442dbea252aef8c0d98fbc7ec9ecc87a55.jpeg) From my understanding, the input layer takes 3 features of an individual from X, so the input layer is merely one individual. These feature values are then put into a linear regression model with wx+b in layer 1, and then thru the sigmoid function into a logistic regression model. What I don’t understand is: if the first node of layer 1 already has values of vector w and it calculated the prediction for training example x given vector w (i.e., y hat), then why is there a need for the other 3 nodes in layer 1?–we already calculated y hat. And from there once it takes all of these y hats, how does it consolidate them into a single y hat in layer 2? Thank you ---
**Author:** ![carlosrl](https://avatars.discourse-cdn.com/v4/letter/c/2acd7d/32.png) [@carlosrl](https://community.deeplearning.ai/u/carlosrl)\ **Post date:** [August 16, 2021, 5:18am UTC](https://community.deeplearning.ai/t/week-3-matrix-w/28914/2 "2021-08-16T05:18:51Z")
Hi @echerny The idea of multiple neurons in DNN, is that each neuron will learn a different feature from the input. So, as more neurons we have, more features the model will learn. But this has a limit. Remember that depending on the network architecture, we need to add dropout to remove some neurons during calculation and avoid overfitting.