Exponentially Weighted Moving Average or Exponential Weighted Average | Deep 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.

[@shreypatel9379]

These are some really good videos. You are unlike all of the indian 'youtube teachers' who target the mundane, less inquisitive audience. Don't stop in making such intuitive videos and maybe who knows you'll be the pioneer of such teaching wave in our country

[@MachineLearningWithJay]

Wow… thank you so much for these kind words. I am glad to see that my content is helping people!

[@kaustubhkapare807]

I think there's one mistake in this video at 3:40 the value of V3 where V2 is substituted....But a really great explanation..!!!

[@MachineLearningWithJay]

Yea… thanks for letting me know

[@Lucas-iy2yr]

I was struggling a lot with this concept in Andrew Ng's Deep Learning specialization. Thank you so much, this is incredibly well explained! You've gained a new subscriber

[@supanutsookkho2749]

I think i'm in the same situation as you. It's really confusing to understand and link the concept here to neural networks. All the best for the rest of the course.

[@Lucas-iy2yr]

@@supanutsookkho2749 Yep, the 2nd course of the specialization is kinda confusing and out of context. Still an incredible specialization and super clear when it comes to NN and gaining intuitions about them, but the code-labs and this part in particular are not that great.

[@vladimirbosinceanu5778]

Very nice job! I needed a second source do understand this concept and this really helped me. Liked and subscribed. Keep em coming and thank you!

[@MachineLearningWithJay]

Glad to hear 😊

[@DhruvBohara-ct4ye]

Crisp and to the point content! Loved it !!

[@vinayakpevekar]

Thanks

[@wailmohamed355]

Thanks for the explanation. The division by (1-B^t) makes v1 = theta1 which is logical to make the average equivalent to the first data point when t=1. However, this division might magnify the average if there are few data points, because (1-B^t) will be small when t is small.

[@arjungoud3450]

Simple & crisp, thank you.

[@MachineLearningWithJay]

😇😇

[@ZirothTech]

Great video! Very clear and easy to follow

[@MachineLearningWithJay]

🙂😇

[@aritahalder9397]

great video, in the 1st 3 mins itself I could grasp the concept..

[@sreenivaskrishna7351]

Fantastic explanation, thank you!

[@omarallam4548]

Great explanation ♥ Thanks

[@MachineLearningWithJay]

Thanks!

[@rajeshpamarthi308]

This helped me to understand, thank you

[@MachineLearningWithJay]

Glad it helped!

[@danishmentalitysaminos3041]

Very well explained !

[@viktoraghajanyan8477]

Very good explanation

[@MachineLearningWithJay]

Thank you so much!

[@feedtowin1309]

Thank you so much for your video!

[@MachineLearningWithJay]

Your welcome!

[@sandeepkomalpothu44]

hey jay !! could you please upload the pdfs of Exponentially weighted Average, Momentum and Rmsprop

[@MachineLearningWithJay]

Hi… I will upload the pdfs and let you know.

[@freeNode5]

But what is θ? Is it for scale?

[@MachineLearningWithJay]

@@freeNode5 Hi, theta is the learnable parameter (eg weights or bias). You can watch my video on linear regression to better understand this.

[@jaydharsandiya3152]

Are you kadva Patel or leva Patel ?

[@MachineLearningWithJay]

Leva 😇

[@MachineLearningWithJay]

Leva 😇

[@jaydharsandiya3152]

😀👍