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

[@dinhh4248]

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

[@NM-el6ps]

Thank you so much

[@JoaoPedro-px5sx]

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!

[@DigitalSreeni]

Great to hear!

[@nate4511]

Finally, someone who speaks math. Thank you sir

[@WahranRai]

22:55 Rule 3 contradiction with rule 2 : input = 50, output = 50 . rule 2 gives hidden

[@Samb12331]

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

[@andrewkicha1628]

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.

[@PatrickBateman12420]

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

[@poffer31]

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

[@DigitalSreeni]

Great to hear!

[@abhilashchaturvedi1479]

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!

[@3DComputing]

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

[@DigitalSreeni]

Well, I try to answer it but in reality it is difficult to definitively answer this question as so much depends on the nature of input data.

[@HK-jw2et]

@@DigitalSreeni kzbin.info/www/bejne/pnW7lZ-OocZ2mdE Hey. Can you pls help me in understanding how many nodes he used in this project. It's a project based on recognising sign language

[@vaibhavs2522]

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

[@DigitalSreeni]

So nice of you

[@devishaarunadevitiwari3988]

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

[@tso8761]

17:53 we can use dropout technique to reduce overfitting btw

[@lakeguy65616]

adding hidden layers without activation functions is essentially linear regression. If the problem is linearly separable, you can find a solution. complex problems with non-linear solutions require hidden layers with activation functions. A more complex solution requires a higher number of hidden layers and activation functions. The "magic" is in the activation function.

[@shipengxu]

Thanks!

[@DigitalSreeni]

Thank you for your kind contribution. Keep watching.

[@vanithas4336]

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

[@shivamsingh-fn8vz]

ok so my doubt is i read on stack exchange and also ur 3 rd point in node section that neuron size should be 2/3 of input size so here the input size is equals to number of unique features or length of features input (len of dataset) and also 2/3 neuron = all the neurons in all the layers or only in single layer

[@momchi2]

many good hints and insights here

[@DigitalSreeni]

Thanks

[@ahmedmoayadalhasani]

Hi Sreeni, I had a significant mistake and training and test data differences. This, in my opinion, is due to the huge values of the output response numbers, which have increased from 64 to over a thousand. Please, how can I resolve this issue? Can I divide them by their maximum value to fix the issue? What do you prefer, please?

[@neerav302]

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

[@DigitalSreeni]

Glad to hear that

[@yacineyacine2951]

this video is like finding gold ... thannnk youuu

[@HK-jw2et]

kzbin.info/www/bejne/pnW7lZ-OocZ2mdE Hey. Can you pls help me in understanding how many nodes he used in this project. It's a project based on recognising sign language

[@troupebase2292]

Thank you for this decent explanation

[@cyruskavwele5304]

Fantastic explanation.

[@grdev3066]

"If your problem can be solved with linear fitting..." Me: trying to survive 2020 ...

[@pfever]

10:43 I think that if the learning rate is too small it could get 'stuck' in a local minima, isn't it?

[@DigitalSreeni]

Depends on the problem.

[@dragnar4743]

So, basically there is no thumb rule. Ofc, it's understandable as it depends on data. So, we have to do hit & trial and observe the loss & accuracy from train-test set.

[@madhumitagiribabu]

thanks much sir found right content after long search

[@aqibfayyaz1619]

Awesome video that is what i was looking for.

[@tahseen4790]

Thanks a lot. I regularly watch your Videos.

[@DigitalSreeni]

Thanks for watching my videos, I donate all money from KZbin advertisements to charity so please thanks for your contribution by watching part of the advertisements.

[@tesfayeabera4978]

please I need an explanation of how to increase the layer of deep belief network from three-layer to more than 6 and its advantages and disadvantage .

[@surajshah4317]

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

[@DigitalSreeni]

They are already on my channel. Please explore videos on my channel.

[@lerneninverschiedenenforme7513]

I didn't understand what's happenning, when the number of hidden nodes increase. Does that also lead to overfitting?

[@DigitalSreeni]

Yes, increasing the number of nodes will also lead to overfitting. Anything that increases the nonlinearity in the model and makes it easy for the model to map training data will lead to overfitting.

[@lerneninverschiedenenforme7513]

@@DigitalSreeni Thank you!

[@ad.donielson]

How about neural network without hidden layer for classification?

[@RajeshSharma-bd5zo]

Great video and well explained!!

[@DigitalSreeni]

Thanks

[@kakshah]

Hi, thank you, may I know which tool is used to make this video?

[@DigitalSreeni]

Not sure what you are asking... can you be a bit specific?

[@dikshitlenka]

Can't we use Keras Tunner to find the exact number of layers and neurons required in the network?

[@DigitalSreeni]

Keras is for hyperparameter tuning and I don't think it is for defining models. I may be wrong as I haven't explored Keras tuner much. If your goal is to find the best model for you problem I recommend AutoKeras.

[@pramishprakash]

Great video sir

[@rfreeman057]

Excellent video!

[@domenicobezuidenhout1587]

For my thesis I am using weather data to predict future values using the CNN but for my loss and Val loss I get nan values? Do you know of a way I could fix this sir?

[@DigitalSreeni]

There are many reason why you’d get a NaN for loss and the most probably reason is high learning rate. If your learning rate is 0.01 try changing it to 0.001 and see if that helps.

[@danielniels22]

thanks sir, this is such an enlightenment 😂 ive been using 4 or even 6 layers by thinking that the model could learn very deep, like some unrecognized patterns 🤣🤣 but turns out just use 1 to 2 😭😭 thanks sir, im new to your channel this week btw 🙏

[@DigitalSreeni]

Great to hear!

[@somewhereinparallelunivers4226]

I have 7lakhs data.so can you suggest me how many neuron can i use for my neural network.. i am using curve fitting neural network.

[@tharindukanchana2077]

Thank you sir, very nice explanation

[@DigitalSreeni]

You're most welcome

[@shubhamsongire6712]

Powerful explination

[@hahavv7058]

excellent vedio that give me great help!think you sir~

[@DigitalSreeni]

You are most welcome

[@heliyahasani6859]

Least Squares Optimizer is same as Analytical Solution.(Wrote this comment to avoid confusion :) )

[@aomo5293]

error again when calculating mean squared error ! line 71 you should use: np.mean((y_test--pred)**2) not np.mean(y_test-y_pred)**2 !! Thank you for good content

[@TheConsoleMania]

the number of neurons in both hidden layer, should be the same?

[@DigitalSreeni]

No, they can be anything.

[@TheConsoleMania]

@@DigitalSreeni yeah, but if I follow the rules in the video, i obtain about 12 neurones. This number should be the same on both hidden layer ? Or maybe the second one should be smaller ?

[@TheConsoleMania]

@@DigitalSreeni I have 12 input and 1 output

[@mojoway9379]

Thanks for the video very helpful

[@SomenathChakraborty]

Could you provide the data source details but it is very small dataset with very limited parameter. But I appreciate your video for clear clarification of the concept.

[@ssonicmoumed]

Thank you, great explanation.

[@DigitalSreeni]

Glad it was helpful!

[@pallavi_4488]

you are worth listening

[@DigitalSreeni]

Thank you very much.

[@abderrahmaneherbadji5478]

Many thanks

[@DigitalSreeni]

You're welcome.

[@tehpson]

OMG thank you, I finallyu understand

[@NoamRathaus]

TLDR; 1 or 2 hidden layers - or just guess because he doesnt know

[@DigitalSreeni]

This is an educational video intended to train the viewer on the implications of number of neurons and hidden layers. In fact, I try to design my content such a way that the viewer gains incremental knowledge on a specific topic. I am sorry if the title set a different expectation to you.

[@علیشمسی-س7ب]

سلام.Hi