Cost Function in Neural Network | Types of Cost function we use in different applications

In this video, we will see what is Cost Function, what are the different types of Cost Function in Neural Network, and which cost function to use, and why.

We will also see Loss Function. Loss function is the term used to represent the error for 1 observation. While Cost function is the term used for the average of errors for all the observation.

We will see Cost Function for 3 different types of problems :
1.) Regression or Linear Regression in Neural Network
2.) Binary Classification in Neural Network
3.) Mulit-class Classification in Neural Network

Timestamps:
0:00​ - Agenda of the video
0:28 - What is Cost Function
1:09 - Cost Function for Regression problem in Neural Network
3:14 -Binary classification Cost Function in Neural Network
6:43 - Multi-class classification Cost Function in Neural Network
9:09 - Summary

➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖

This is Your Lane to Machine Learning ⭐

➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖

➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖

[MachineLearningWithJay]

If you found this video helpful, then hit the *_like_* button👍, and don't forget to *_subscribe_* ▶ to my channel as I upload a new Machine Learning Tutorial every week.

[naveenkv]

In a few years I can't help but think your videos on machine/deep learning concepts are going to be recommended by many teachers for basic understanding. Nicely explained.

[PrithaMajumder]

Thanks a lot for This Amazing Introductory Lecture 😁
Lecture - 4 Completed from This Neural Network Playlist

[adnanhowlader]

Thanks for making this..I feel like there is not enough explanation about this topic in YouTube

[tiyyob]

Splendid work. The way you explained it with example is a tremendous help.

[S.aliakbar.h]

You are a good teacher. Congratulations ❤

[ISMAIL-dlgw]

Thank you for your excellent explanation

[manikantaperumalla]

cost function for binary classification that you mentioned is also called as entropy.
am I right?

[bonpagnakann]

thank you very much for this video! I appreciate your effort in simplifying this. I would like to check with you about the cost for Multi-class classification in sigma whether there should be (1/m) for many observations in the training 9:00 ? Because I saw you include (1/m) for the average for binary classification, but I did not see you including it in the Multi-class classification. Thank you in advance for your response. ^^

[Ivaan_reminiscence]

when you summarized the formula @9:00 min, wont there be an 1/m upfront? as that's what you explained at the top handwritten

[learnhome]

Great Chapter, Really Appreciate your efforts...You can become another Sal Khan...One suggestion, the animated pointer feels disturbing to eyes, You may use a normal one instead

[PavanKumar-hpel]

My doubt is can't we get y = [1, 0, 1, 0] if we have (predicted output) a = [0.5, 0.2, 0.8, 0.3] ?? what is the guarantee that we always get only one element in a is having >= 0.5 ??

[shahfahad]

Can you suggest a book which you follow for classification and its cost function

[harshitjuneja]

for multi-class classification, do we not add a (1-y)log(1-a) term?

[md.enamulatiq]

Can you plz provide the slides you used for these videos?

[AnbuArasu-fgss]

What if the actual value is 0 and the predicted value is 1.

Will the error be infinite.

[indrayudhmondal]

This guy teaches better than my professor.