#1 Solved Example Back Propagation Algorithm Multi-Layer Perceptron Network by Dr. Mahesh Huddar

[@ervincsengeri1840]

Köszönjük!

[@MaheshHuddar]

Welcome Do like share and subscribe

[@akinyaman]

man l looked many bp explanations and most of them telling of rocket science stuff this is the easy and clear one ever, thanx for sharing

[@safayetsuzan1951]

Sir, you deserve a big thanks. My teacher gave me an assignment and i was searching for 2 days on youtube for weight calculation. But finally your video has done the work. It was really satisfying. Thank you sir.

[@MaheshHuddar]

Welcome Do like share and subscribe

[@joeystenbeck6697]

This makes the math very clear. I now know the math and have some intuition, so I hope to fully connect the two soon. Thanks for the great video!

[@MaheshHuddar]

Thank You Do like share and subscribe

[@shivamanand8019]

It looks like error in ∆wji notation you followed just opposite @@MaheshHuddar

[@jarveyjaguar4395]

I have an Exam in 2 days and your videos just saved me from failing this module. Thank you so much and much love from 🇩🇿🇩🇿.

[@MaheshHuddar]

Welcome Do like share and subscribe

[@tejasvinnarayan2887]

Very clear! How about bias b? What is the formula in case we add a bias?

[@horiashahzadi302]

Boht zbrdast lecture ha ....boht shukrya....keep it up

[@abu-yousuf]

Great work Dr. Mahesh. Thanks from Pakistan.

[@MaheshHuddar]

Welcome Do like share and subscribe

[@alperari9496]

I believe for hidden units, the w_kj in delta(j) formula should have been w_jk. Namely, other way around.

[@alperari9496]

And delta(w_ji) should have been delta(w_ij), again the other way around.

[@steveg906]

yeh i was about to comment the same thing

[@SumOfBody]

And the aj calculations conflict with the formula posted. Either its for j in wi: aj = sum(wij * xi) [what the equation is] or it's for i in w: aj = sum(wij * xi) [what the calculations are] Pretty sure the formula is correct but the calculations are wrong.

[@R41Ryan]

Thank you. I've been trying to implement a reinforcment algorithm from scratch. I understood everything except back propogation and every video on it that I've watched has always been vague until I saw this video. Good stuff!

[@MaheshHuddar]

Welcome Do like share and subscribe

[@BloodX03]

Damn sir, u are the best youtube teacher in AI.. Love youu ma sir

[@shreyaankrao968]

I got crystal clear understanding of this concept only because of you sir. The flow of video is excellant, appreciate your efforts!! Thank you and keep up the good work !!

[@MaheshHuddar]

Welcome Do like share and subscribe

[@khizarkhan2250]

Guys! Threshold or bias is a tunning parameter you can select something low like 0.01 , 0.02 or high like 0.2 to check error is getting low or not. I hope this will help you.

[@ToriliaShine]

thank you! understood the concept smoothly with your video!

[@MaheshHuddar]

Thank You Do like share and subscribe

[@ToriliaShine]

@@MaheshHuddar did that, question though. for the forward pass, what about biases? they are values with their own weights right. were they just, not included for this example?

[@ToriliaShine]

ah nevermind, got it from your next video in this series lol

[@paul-pp1op]

Best video explanation on ANN back propagation. Many thanks sir

[@MaheshHuddar]

Thank You Do like share and subscribe

[@brandoncazares8452]

Thank you very much, sir. This helped me understand better.

[@kronten3662]

Thank you sir paper mai 10 marks ka pura Ane ke liye

[@satriohalim7213]

Thank you so much sir for this informative explanations. Lot of respect from me

[@alibabarahaei2229]

Perfect❤

[@vnbalaji7225]

Simple lucid example illustrated. Please continue.

[@MaheshHuddar]

Thank You

[@web3sorcerer]

this is a great lecture!

[@ushanandhini1942]

Easy to understand. Give next one is CNN

[@NotLonely_Traveler]

Finally one that makes sense

[@MaheshHuddar]

Thank You Do like share and subscribe

[@Ayesha_01257]

Very Well Explained ...Keep up the Good Work

[@MaheshHuddar]

Thank You Do like share and subscribe

[@hendsaleh7428]

Thank you so much 💓 U r the best 👌

[@sharanyas1565]

Very clear. Thanks for uploading this video.

[@MaheshHuddar]

Welcome Do like share and subscribe

[@mdnahidulislam13]

Clear explanation. recommanded...

[@MaheshHuddar]

Thank You Do like share and subscribe

[@sahmad120967]

Great sir, it is very clear example how to calculate ANN. Thanks, keep being productive

[@MaheshHuddar]

Thank You Do like share and subscribe

[@25fpslagger81]

Thank you sir, all of you machine learning videos have helped us students a lot

[@MaheshHuddar]

Welcome Do like share and subscribe

[@hemanthd623]

@@MaheshHuddar Sir Can you solve problems on HMM , CNN pls

[@msatyabhaskarasrinivasacha5874]

It'd an awesome explanation sir....no words to thank you sir

[@MaheshHuddar]

You are most welcome Do like share and subscribe

[@lalladiva6097]

you are a life saver, thank you soooo much.

[@MaheshHuddar]

Thank You Do like share and subscribe

[@df_iulia_estera]

Awesome explanation! Thanks a lot!

[@MaheshHuddar]

Thank You Do like share and subscribe

[@alizainsaleem5533]

best explanation

[@pritam-kunduu]

You taught Very good. Today is my exam. Your videos were really helpful. I hope I pass well without getting a backlog in this subject. 👍👍

[@MaheshHuddar]

Welcome Do like share and subscribe

[@AbhishekSingh-up4rv]

Awesome explanation. Thanks

[@MaheshHuddar]

Welcome Do like share and subscribe

[@srisangeeth4131]

Concept is clear , i got confidence in this concept sir,thank you👍👍👍👍

[@MaheshHuddar]

Welcome Do like share and subscribe

[@srisangeeth4131]

@@MaheshHuddar sir can you provide videos in gaussian process in machine learning

[@TigistAyeleHabte]

really helpfull thank you

[@sahanazbegam6913]

very clear thank you for the content

[@MaheshHuddar]

Welcome Do like share and subscribe

[@arminmow]

You saved me you're a hero thank you

[@MaheshHuddar]

Welcome Do like share and subscribe

[@iwantpeace6535]

THANK YOU SIR , BIRILIANT INDIAN MIND

[@MaheshHuddar]

Welcome Do like share and subscribe

[@MissPiggyM976]

Very useful, thanks!

[@MaheshHuddar]

Welcome Do like share and subscribe

[@a5a5aa37]

thanks a lot for your explanation!

[@MaheshHuddar]

Welcome Do like share and subscribe

[@user-fl7bm8jc8o]

Thanks a lot sir 🙏🙏🙏🙏🙏🙏🙏

[@MaheshHuddar]

Most welcome Do like share and subscribe

[@femiwilliam1830]

Good job, but why no account for the bias term before applying sigmoid function?

[@kanikavinayak7586]

love from tiet 👏👏

[@tanvirahmed552]

Nice video, easily understood the topic, thank you

[@MaheshHuddar]

Welcome Do like share and subscribe

[@flakysob]

Thank you so much! You saved me. I subscribed. Thanks

[@MaheshHuddar]

Welcome Please do like share

[@tatendamachikiche5535]

good staff thank u

[@MaheshHuddar]

Welcome Do like share and subscribe

[@romankyrkalo9633]

Great video, easy to understand

[@MaheshHuddar]

Thank You Do like share and subscribe

[@ajayofficial3706]

Thank you Sir, for each and every point explain it.

[@MaheshHuddar]

Welcome Do like share and Subscribe

[@adilmughal2251]

Amazing stuff just to the point and clear.

[@MaheshHuddar]

Thank You Do like share and subscribe

[@AnubhavApurva]

Thank you!

[@MaheshHuddar]

Welcome Do like share and subscribe

[@sathviksrikanth7362]

Thanks a lot Sir!!!

[@MaheshHuddar]

Welcome Do like share and subscribe

[@bagusk_awan]

Sir, thank you for this great video! It was really helpful. I appreciate the clear explanation

[@MaheshHuddar]

Glad it was helpful! Do like share and subscribe

[@mr.commonsense6645]

GOATED Explaning, mantab mantab

[@usmanyousaaf]

Today is my exam again well explain sir

[@iqramunir1468]

Thank you so much sir

[@MaheshHuddar]

Welcome Do like share and subscribe

[@utkarshmangal6559]

you are a king sir. Thank you for saving me from my exam tommorow.

[@MaheshHuddar]

Welcome Do like share and subscribe All the very best for your exams

[@jacki8726]

Very helpful

[@MaheshHuddar]

Do like share and subscribe

[@usmanyousaaf]

Last night !! Today is exam well explain boss

[@TXS-xt6vj]

you are a legend

[@MaheshHuddar]

Welcome Do like share and subscribe

[@umakrishnamarineni3520]

thank you sir.

[@MaheshHuddar]

Most welcome Do like share and subscribe

[@shubhampamecha9650]

And where is the b biased There should be some constant also?

[@allahthemostmerciful2706]

Soooooo Good❤

[@MaheshHuddar]

Thank You Do like share and subscribe

[@tlbtlb3950]

不错，老印！

[@arj1045]

well done sir

[@MaheshHuddar]

Thank You Do like share and subscribe

[@jinkagamura2820]

I have a doubt. In many places, I have seen that the error calculation is done using the formula E = 1/2 (y - y*)^2, but you have calculated by using subtraction. Which is correct?

[@keertichauhan6221]

same doubt .. what is the correct method?

[@priyanshumohanty5261]

@@keertichauhan6221 I think there are different methods to compute the error. The one that this guy above has mentioned is mean square error. The one shown in the video is also correct, but using MSE or RMSE, are generally regarded as better measures.

[@chukwuemekaomerenna4396]

For a multiple data point, you use error function and for single output you make use of loss function. Loss function is error = actual - target Error function is 1/2(actual-target)square

[@chukwuemekaomerenna4396]

For a multiple data point, you use error function. Error function=1/2 summation(y actual - y target)^2. For a single data point, you use the loss function. Loss function= (y actual - y target)

[@sharanyas1565]

The errors are made to be positive by squaring.

[@bharatreddy972]

Thank you So much Sir.....This videos made us clear understanding of Machine learning all concepts...

[@MaheshHuddar]

Welcome Do like share and subscribe

[@AmnaCode]

Thanks for solution

[@MaheshHuddar]

Welcome Do like share and subscribe

[@AmnaCode]

@@MaheshHuddar sure. Thanks 😊

[@madhusaggi]

Can you please do vedios on Cnn with mathematical concepts..your vedios are much useful and understandable.Thank you

[@jeyak9719]

DID YOU SKIP THE BIAS WHILE TEACH

[@bhuvanareedy]

Is this suitable for nueral networks

[@mehmetakifvardar]

Mr.Huddar, thanks a lot for perfect explanation. One thing though, how do I calculate the change of bias term for each neuron in my neural network?

[@SaiNath-cw7yn]

thank u sir

[@MaheshHuddar]

Welcome Do like share and subscribe

[@dydufjfbfnddhbxnddj83]

how did you update the weights of connections connecting input layer and the hidden layer?

[@tuccecintuglu404]

YOU ARE THE GBEST

[@SHUBHAMKUMAR-cd7fs]

awesome.

[@MaheshHuddar]

Thanks! Do like share and subscribe

[@believer-n3t]

sir while making neuron what should be our initial weight. how to decide that

[@ram-pc4wk]

how are you deriving deltaj formula, u can include derivations of sigmoid functions.

[@pranavgangapurkar195]

in one epoch how many times back propagation takes place?

[@makkingeverything6610]

thank you man

[@MaheshHuddar]

Welcome Do like share and subscribe

[@imranimmu4714]

thank you

[@MaheshHuddar]

Welcome Do like share and subscribe

[@priyaprabhu7101]

Nice Video sir.. where is the bias here

[@지엔서]

good video

[@MaheshHuddar]

Thank You Do like share and subscribe

[@ayushhmalikk]

youre a legend

[@MaheshHuddar]

Thank You Do like share and subscribe

[@LongZzz]

Thank you so much, this video comes right after I feel bad at machine learning and wanna give up but now I think it is not so hard as I think

[@MaheshHuddar]

Welcome Do like share and subscribe

[@Gaurav-z6l1c]

i just wanted to know that these calculation equation for weight are same for all neural network or it is for the specific one?

[@oposicionine4074]

How do you update de weights if you have more input data?? In this case he only has 1 input, how do you do it with 2 inputs? Do you do the same twice?

[@animeclub8475]

everyone says "thank you", but only a few understand that this video is useless if there are more neurons on one layer. Those who say "thank you" do not even plan to make a neural network

[@ishrarchowdhury4850]

check the algorithm. you take 1 input, then update the weights. then you take the next one. in this way you continue till all the data points. you do this epoch number of times.

[@AmarAmar-q8s]

Hey man, how to reach out you?

[@sowmiya_rocker]

Thanks for the video, sir. I have a doubt. How did you update weights without Gradient Descent (GD) or any other optimization technique, sir? Because I read in blogs that Networks don't get trained without GD and by only using backpropagation. In other words, my doubt is how does the calculation change if we also implemented GD in this? I'm a rookie; kindly guide me, sir.

[@adityachalla7677]

gradient descent has been used in this video while updating the weights. the change in weights is done through gradient descent. But here he has not written the derivative math.

[@rohanwarghade7111]

how he got ytarget = 0.5@@adityachalla7677

[@lakshsinghania]

sir, also each perceptron has bias with it right ?

[@MaheshHuddar]

Yes

[@MaheshHuddar]

Follow this video for bias: kzbin.info/www/bejne/pGOvYn1rf76ai80

[@lakshsinghania]

Thank u sir a lot!! @@MaheshHuddar

[@pubuduchanna1736]

Thank you! This helped me a lot!

[@MaheshHuddar]

Welcome Do like share and subscribe

[@justenjoy3744]

From which book u have taken problem from?

[@amulyadevireddy5669]

What about the bias factor??

[@halihammer]

He did not add it to keep it simple i guess. But you can add the bias by making it a third input. Then the method doesnt change you just have a new (constant) input for each layer. Normaly set to one 1 and the weight associated will act as your bias. since 1*biasWeight = biasWeight. I just added 1 to my input vector and generate an additionol weight for the weights matrix. But im also just learning an not sure if im 100% correct..

[@JudyXu-d6j]

I have a question, what if we have a bias term and some bias weights. Do we need to account for those or it would be 0?

[@MaheshHuddar]

Yes you have to consider Follow this video: kzbin.info/www/bejne/pGOvYn1rf76ai80

[@satwik4823]

GODDD!!!!!!!!!!!!!!!!!!!

[@MaheshHuddar]

Thank You Do like share and subscribe

[@pritampatil4669]

What about the bias terms ?

[@seabiscuitthechallenger6899]

👍👍👍👍👍👍👍👍

[@MaheshHuddar]

Thank You Do like share and subscribe

[@kaavyashree6209]

Sir how to update bias in back propagation

[@MaheshHuddar]

Refer this video: kzbin.info/www/bejne/pGOvYn1rf76ai80

[@Professor_el]

The formulars for delta W only work because of the nature of the actiation function right? if it is a hyperbolic tangent or RELU , the formulas change right?

[@steveg906]

yes

[@muhtasirimran]

I have a confusion. We use ReLU on hidden layer and not sigmoid. Shouldn't we calculate hidden layer's activation using ReLU instead of sigmoid?

[@MaheshHuddar]

Yes you have to Do calculation Based on activation function

[@muhtasirimran]

@Mahesh Huddar ik. You have used sigmoid function on the hidden layer. This will result in an error.