155 - How many hidden layers and neurons do you need in your artificial neural network?

No one can give a definite answer to the question about number of neurons and hidden layers. This is because the answer depends on the data itself. This video goes through the thought process of determining the number of hidden layers and neurons using simple code as example.

#Dataset link:

Code generated in the video can be downloaded from here:

[Samb]

You are an amazing teacher, I hope this comment reaches you well! This is some top class free content! Thank you!

[dinhh]

16:36 is the answer for how many layers do you need

[JoaoPedro-pxsx]

Those were some of the best explanations about hidden layers and numbers of neurons I could find, also making it very easy to see in your python plots. Keep up the good work!

[abhilashchaturvedi]

I really loved your approach. You are explaining the technicalities and discussing the various possibilites while staying on the subject. It's thorough. With other youtubers, I felt like they were too basic and missing the crucial implementation part. Thankyou!

[AdobadoFantastico]

This is a fantastic explanation. I really appreciate how you involved the math as you walked through your implementation. A lot of people hand wave the math.

[wuzark]

This is such an intuitive and helpful video. I can see that there is a lot of hard work behind this video. Great job!

[nate]

Finally, someone who speaks math. Thank you sir

[andrewkicha]

Such a wonderful explanation to the really fundamental question. I wonder why there is so little accessible information for beginners on this topic.
Thanks a lot for the video.

[PatrickBateman]

Finally, an explanation that goes straight into code. Awesome!

[poffer]

The approach to explaining it trough linear regression was very useful for me, thank you!

[devishaarunadevitiwari]

Thanks for giving clarity on such an important notion. worth it.

[aqibfayyaz]

Awesome video that is what i was looking for.

[vaibhavs]

I don't know why there are too few likes on such an awesome video..you are really great sir.

[tahseen]

Thanks a lot. I regularly watch your Videos.

[madhumitagiribabu]

thanks much sir found right content after long search

[neerav]

You are awesome .. you taught me this topic like pro

[vanithas]

Amazing..helps me lot for my research work. Thanks

[WahranRai]

22:55 Rule 3 contradiction with rule 2 : input = 50, output = 50
. rule 2 gives hidden <= 50
. rule 3 (not clear) : hidden = (2/3) *50 + 50 ~ 83 or hidden = (2/3) *(50 + 50) ~67 then hidden not between input and output

[DComputing]

Strange isnt it, so many people asking THIS question, and so few people can answer it, THANK YOU

[surajshah]

wow, thank you so much for the great video. Sir can you make videos on segmentation using GAN and UNet ??