# C3\_W2\_Collaborative\_RecSys\_Assignment: Wrong data for Regularization **URL:** \ **Category:** Unsupervised Learning, Recommenders, Reinforcement\ **Tags:** week-module-2\ **Created:** [November 6, 2024, 5:13pm UTC](https://community.deeplearning.ai/t/c3-w2-collaborative-recsys-assignment-wrong-data-for-regularization/719444 "2024-11-06T17:13:27Z")\ **Posts on this page:** 12\ **Page:** 1
**Author:** ![ravivemuri](https://avatars.discourse-cdn.com/v4/letter/r/9de053/32.png) [@ravivemuri](https://community.deeplearning.ai/u/ravivemuri)\ **Post date:** [November 6, 2024, 5:13pm UTC](https://community.deeplearning.ai/t/c3-w2-collaborative-recsys-assignment-wrong-data-for-regularization/719444/1 "2024-11-06T17:13:27Z")
Hi, I have an issue for the C3\_W2\_Collaborative\_RecSys\_Assignment Exercise 1 In the steps it is asked to compute cofi\_cost\_func with and without regularization In the function towards the end, where J is computed, As it asks to compute J without regularization first followed by with regularization, and since it is the same function call, I added like this if(lambda\_ == 0): J += else : J += Is this approach correct? I dont get any syntax error, but the value of J that is returned WITH regularization is wrong. I am getting 144.43, whereas expected is 28.09 Can you please help me where I am going wrong? Regards Ravikiran ---
**Author:** ![TMosh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/tmosh/32/9321_2.png) [@TMosh](https://community.deeplearning.ai/u/TMosh)\ **Post date:** [November 6, 2024, 5:17pm UTC](https://community.deeplearning.ai/t/c3-w2-collaborative-recsys-assignment-wrong-data-for-regularization/719444/2 "2024-11-06T17:17:06Z")
That’s not a necessary approach. I recommend you implement only the code for the regularized cost, and if lambda = 0, then that contribution will be zero because it is a multiplier. > [@ravivemuri](#): > > the value of J that is returned WITH regularization is wrong. That indicates your calculation is incorrect. ---
**Author:** ![ravivemuri](https://avatars.discourse-cdn.com/v4/letter/r/9de053/32.png) [@ravivemuri](https://community.deeplearning.ai/u/ravivemuri)\ **Post date:** [November 6, 2024, 5:32pm UTC](https://community.deeplearning.ai/t/c3-w2-collaborative-recsys-assignment-wrong-data-for-regularization/719444/3 "2024-11-06T17:32:27Z")
But then I am getting error for the previous one where we calculate WITHOUT regularization where the expected output is 13.67 which I got with the different formula? I guess there are two different formulas for with and without. Is that not correct? ---
**Author:** ![TMosh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/tmosh/32/9321_2.png) [@TMosh](https://community.deeplearning.ai/u/TMosh)\ **Post date:** [November 6, 2024, 6:43pm UTC](https://community.deeplearning.ai/t/c3-w2-collaborative-recsys-assignment-wrong-data-for-regularization/719444/4 "2024-11-06T18:43:45Z")
There is only one equation for the cost. This image is from Section 4.1 of the notebook: ![image](https://global.discourse-cdn.com/dlai/original/3X/c/d/cd5718678ba7b95bf2560ffee220adb20dd39093.png) The part labeled A is the unregularized cost. The part labeled B is the regularized portion of the cost. If the cost function is called with the lambda parameter set to 0, then the B portion will compute to 0, so the function returns only the unregularized cost. If you don’t get the correct results for the A portion, there is an error in your code. ---
**Author:** ![ravivemuri](https://avatars.discourse-cdn.com/v4/letter/r/9de053/32.png) [@ravivemuri](https://community.deeplearning.ai/u/ravivemuri)\ **Post date:** [November 6, 2024, 7:30pm UTC](https://community.deeplearning.ai/t/c3-w2-collaborative-recsys-assignment-wrong-data-for-regularization/719444/5 "2024-11-06T19:30:24Z")
I am kind of little lost. From the “hints” portion of the exercise, it showed two different equations for w/o regularization and with regularization. As per your tip, I should still use the equation for “regularization” and since lambda will be 0, it should work for w/o regularization also? Let me try Ravikiran ---
**Author:** ![ravivemuri](https://avatars.discourse-cdn.com/v4/letter/r/9de053/32.png) [@ravivemuri](https://community.deeplearning.ai/u/ravivemuri)\ **Post date:** [November 6, 2024, 8:13pm UTC](https://community.deeplearning.ai/t/c3-w2-collaborative-recsys-assignment-wrong-data-for-regularization/719444/6 "2024-11-06T20:13:42Z")
I am not sure if I am getting the correct value after following the equation. I am stuck at this place. I am aware that I am not supposed to paste the code here, but please delete it after I get the fix for this. Please let me know what I did below is correct? {mentor edit: code removed} With regularization, I am getting a value of 302.13, while expected is 28.09 Please help Ravikiran ---
**Author:** ![TMosh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/tmosh/32/9321_2.png) [@TMosh](https://community.deeplearning.ai/u/TMosh)\ **Post date:** [November 6, 2024, 8:34pm UTC](https://community.deeplearning.ai/t/c3-w2-collaborative-recsys-assignment-wrong-data-for-regularization/719444/7 "2024-11-06T20:34:14Z")
Please do not share your code on the forum. That’s not allowed by the Code of Conduct. You can send me your code via a private message, I’ll send you instructions in a moment. Also note that the “preformatted text” tag should be used so that your code indentation is preserved. ---
**Author:** ![ravivemuri](https://avatars.discourse-cdn.com/v4/letter/r/9de053/32.png) [@ravivemuri](https://community.deeplearning.ai/u/ravivemuri)\ **Post date:** [November 6, 2024, 9:27pm UTC](https://community.deeplearning.ai/t/c3-w2-collaborative-recsys-assignment-wrong-data-for-regularization/719444/8 "2024-11-06T21:27:47Z")
Thank you, yes I am kind of aware not to do. Probably I should have asked how to do private message. Sorry and thank you ---
**Author:** ![TMosh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/tmosh/32/9321_2.png) [@TMosh](https://community.deeplearning.ai/u/TMosh)\ **Post date:** [November 7, 2024, 12:03am UTC](https://community.deeplearning.ai/t/c3-w2-collaborative-recsys-assignment-wrong-data-for-regularization/719444/9 "2024-11-07T00:03:17Z")
Report back for students who find this thread later: - Be sure that if you compute the regularized cost for all values of X and W, that you do so only once (outside of any nested for-loops). ---
**Author:** ![LaurenRitter](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/laurenritter/32/111104_2.png) [@LaurenRitter](https://community.deeplearning.ai/u/LaurenRitter)\ **Post date:** [February 18, 2025, 9:56pm UTC](https://community.deeplearning.ai/t/c3-w2-collaborative-recsys-assignment-wrong-data-for-regularization/719444/10 "2025-02-18T21:56:37Z")
Hi @TMosh I was wondering if you might be able to help me here as well? I have been struggling on this lab in particular this week and am truly unsure what I might be doing wrong, even after studying the tips provided. ---
**Author:** ![TMosh](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/tmosh/32/9321_2.png) [@TMosh](https://community.deeplearning.ai/u/TMosh)\ **Post date:** [February 18, 2025, 10:13pm UTC](https://community.deeplearning.ai/t/c3-w2-collaborative-recsys-assignment-wrong-data-for-regularization/719444/11 "2025-02-18T22:13:52Z")
What problem are you having specifically? Please don’t post your code, just a description of the issue, and a screen capture image of any error messages or test results you see in your notebook. ---
**Author:** ![LaurenRitter](https://sea1.discourse-cdn.com/dlai/user_avatar/community.deeplearning.ai/laurenritter/32/111104_2.png) [@LaurenRitter](https://community.deeplearning.ai/u/LaurenRitter)\ **Post date:** [February 19, 2025, 4:23pm UTC](https://community.deeplearning.ai/t/c3-w2-collaborative-recsys-assignment-wrong-data-for-regularization/719444/12 "2025-02-19T16:23:58Z")
Thank you for responding! I slept on it and this morning realized it was the order in which I included the regularization term. Once I fixed this, all the tests passed. Thanks for your time, cheers!