Hello! I hope you are doing well. I’ve completed all the courses of MLS and the first course of DLS. Now I am creating my own NN model from scratch, using random data. However, I am facing some issues (attached picture). I am using relu for both hidden and output layers (input = numerical value; ou…

It seems you are dividing by zero is the problem and is probably the A variable, which as far as I remember are the weights AX+B (right?), so you need to have a look where exactly this division by zero is happening and fix it. I am guessing you might be initializing the weights all to zero maybe its…

A is np.maximum(0,Z) while Z is np.dot(W,X) + b I cannot figure out where that division by zero is. I initialized weights randomly, multiplying by 0.01. Actually, I copied all the functions from DLS_C1_W4_assignments and changed the input, output, and little modifications. But still struggling to…

Was there any inf or nan in your (normalized) data? You may check it with np.isinf(...) and np.isnan(...)

I just checked this. All are False, means no nan or inf. I generated data like this: x = np.arange(0, 20, 1) y = 3*x**2 + 3 X = x.reshape(-1, 1) y = y.reshape(-1,1)

You probably have negative values inside the np.log, which gives nan.

Well either np.log(AL) or np.log(1-AL) is becoming negative, so make sure to trace it why is it becoming negative and avoid it to become negative. I dont remember the notation right now but that your start.

Your data is a regression problem. Which cost function are you using? What is the activation function in the NN’s last layer?

cost = - np.sum(np.multiply(np.log(AL),Y) + np.multiply(np.log(1-AL),(1-Y)))/m cost = np.squeeze(cost) I am using relu for both hidden and output layers.

So this is the problem. From your data it is a regression problem, but you are not using a cost function for a regression problem. Your NN can produce very large positive number which will trigger the problem as @gent.spah explained.

Personal project issues

AI Discussions

rmwkwok November 19, 2022, 3:08pm 17

Hello @saifkhanengr! I think this post has the answer. Also you are using ReLU for hidden layers as well, so that is your reference.

Topic		Replies	Views
Derivative of Relu in output layer Neural Networks and Deep Learning coursera-platform	125	3296	December 23, 2022
Week 4 Assignment 3 Exercise 1 Neural Networks and Deep Learning week-module-4 , coursera-platform	8	395	January 26, 2024
NAN as results for the cost computations Neural Networks and Deep Learning coursera-platform	27	811	December 27, 2021
Divide by zero log error encountered when images dimension becomes larger Neural Networks and Deep Learning coursera-platform	5	595	October 5, 2021
Nan in week 3 assignment Neural Networks and Deep Learning coursera-platform	10	751	May 2, 2021

Personal project issues

Related topics