\ **Category:** TF.js\ **Tags:** tfjs\ **Created:** [March 13, 2023, 5:51pm UTC](https://discuss.ai.google.dev/t/tensorflow-js-a-simple-runnable-example-that-crashes-in-browser/31133 "2023-03-13T17:51:44Z")\ **Posts on this page:** 4\ **Page:** 1

**Author:** ![Mah\_Neh](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/mah_neh/32/11663_2.png) [@Mah\_Neh](https://discuss.ai.google.dev/u/Mah_Neh)\ **Post date:** [March 13, 2023, 5:51pm UTC](https://discuss.ai.google.dev/t/tensorflow-js-a-simple-runnable-example-that-crashes-in-browser/31133/1 "2023-03-13T17:51:44Z")

So I am following a course in Coursera and decided to play a bit with the code, here it is my simple runnable code that you can run by launching a live server in vs code: ```javascript

Hello World

``` - If the lr is 0.1 it crashes - If the lr is 0.01 it gets to the minimum Any ideas why is this so? ---

**Author:** ![Jason](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/jason/32/6193_2.png) [@Jason](https://discuss.ai.google.dev/u/Jason)\ **Post date:** [March 14, 2023, 1:54am UTC](https://discuss.ai.google.dev/t/tensorflow-js-a-simple-runnable-example-that-crashes-in-browser/31133/2 "2023-03-14T01:54:40Z")

I am unfamiliar with the Coursera course but I cover these areas in my YouTube series over on Google Developers for Web ML: https://www.youtube.com/embed/7cOv4Uqilt4?feature=oembed&wmode=opaque&list=PLOU2XLYxmsILr3HQpqjLAUkIPa5EaZiui Essentially 0.1 is probably too high and you may never converge to a reasonable fit for your data. See my visuals in this video above around 8 mins - but see the whole video for the context. ---

**Author:** ![Mah\_Neh](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/mah_neh/32/11663_2.png) [@Mah\_Neh](https://discuss.ai.google.dev/u/Mah_Neh)\ **Post date:** [March 14, 2023, 12:02pm UTC](https://discuss.ai.google.dev/t/tensorflow-js-a-simple-runnable-example-that-crashes-in-browser/31133/4 "2023-03-14T12:02:20Z")

Nice! I was trying to plot something like that, but didnt get there yet. I wonder how this happens though, I also found out that normalizing the data is essential… ---

**Author:** ![Jason](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/jason/32/6193_2.png) [@Jason](https://discuss.ai.google.dev/u/Jason)\ **Post date:** [March 14, 2023, 7:31pm UTC](https://discuss.ai.google.dev/t/tensorflow-js-a-simple-runnable-example-that-crashes-in-browser/31133/6 "2023-03-14T19:31:10Z")

Yep I cover Normalization here: https://www.youtube.com/embed/hfwnQR8qyv0?feature=oembed&wmode=opaque&list=PLOU2XLYxmsILr3HQpqjLAUkIPa5EaZiui&start=294 at around 4min 54 sec.