the screetching noise is irrtitaing..else nice tutoial

wow, one of the best highlights of activation functions on the internet. Thank you for doing this video

Awesome as always. Some points to ponder correct me if I am wrong 1. Relu is just not a activation but can also be thought as a self regularizer, as it offs all those neurones whose values are negative, so it's just a kind of automatic dropout. 2. A neutral net with just input and output layer, with softmax at the output layer is logistic regression, but when we add hidden layers in this network with no hidden activations then it's more Powerful than just vanilla logistic regression as it is now taking linear combination of linear combinations with different weight settings. But it still results in linear boundaries. Lastly your contributions to the community is very valuable, clears a lot nitty-gritty details in short time. Keep going like this :)

Straight to the point. Nice and super clean explanation for non-linear activation functions. Thanks!

Great explanation ! and the animations with maths formula and visualizing it is awesome !! Many thanks !

One of the best explanations ive come across

What I was looking for. Thanks!

THIS HELPED SO MUCH! THANK YOU!

Thank you very much for the great, and smooth explanation. This was really perfect.

oh man, amazing explanation.Thanks

Amazing! Finally I am able to visualise vanishing gradient descent and dying relu.

Wooo, Did I just noticed the complex explained simple. Thanks! Looking forward to more videos.

I'm learning deep learning rn and using the deep learning book published by MIT press for the same. That's kinda complicated for me to understand especially these parts cause m still an undergrad and have 0 previous experience with this. Thank you for explaining this so well.

Thank you for sharing! This video cleared my doubts and gave me a good introduction to learn further

Great video ! And what is more great - are the useful references you add at the description. ( For me (1)+(7) answer the questions I asked my self at the end of your video - so its was on point ) ! Thank you !

best explanation of activation functions I ever seen

Excellent explanation. Thank you.

Really awesome video!

Beautiful explanation!

Great video, keep going !

wonderful explanation!!!

Awesome video man !

wow, that was really helpful, thanks a ton!!!!

I discovered your page just yesterday and might I say, YOU'RE AWESOME! Thanks for such good content bro.

This was an amazing video!!! Keep up the good work!

7:48 "once it hits zero the neuron becomes useless and there is no learning" this explains so much, thank you!

thank you very much, this is really helpful

This was really helpful! Thanks!

Great Video. Could you explain what U and V are equal to in this equation : o = Ux + V ? And How did you come up with the decision boundary equation and how did you determine the values of w1 and w2 ? Thanks in advance

The most thing I love about your videos is the fun you add... Learning becomes a bit easier

Amazing presentation ,easy and captivating to grasp

Wow... Perfect and easiest way to explain it.. Everyone talks about what activations do but nobody shows in how actually it looks like behind the algos.. And you explain things in the most easiest way which are so easy to understand and remember.. So a big like for. All your videos.. Could uh make more and more and DL.. 😄

Can you cover tanh activation? (Thanks for making this one so good!)

really helpful..thanks

great .. so many thanks ... need more explanation

this is helpful, thanks :)

Another great video 🎉🎉🎉!

yes! I liked it. Keep it up.

Great explanation for activation function I like it so much

better than most professors, thanks for great video

Great video! The dissapointed gestures were a bit too much x'D A question I did have as a beginner was. What does it mean for a sigmoid gradient to "squeeze" values, as in they become smaller and smaller as they back propagate?

That's great explanation

Amazing explanation and also funny 😅👏👏👏

awesome video

Amazing!

Quality video!

Great Video and great page :) Which softwares you use to make these videos ?

Thanks mate

Thanks man)

can we use linear activation with hinge loss for Linear svm for binary classification.

Nicely explained

good job thank you

good explanation for a beginner

this guy is genius

Great explanation! Had to switch to earphones though :P

@6:24 How does passing what is a straight line into the softmax function also give us a straight line? Isn't the output, and consequently the decision boundary, a sigmoid? Or is it the output before passing it into the activation function what counts as the decision boundary?

it should be possible to let (part of) the net optimize its own activation function no?

good work bro keep it up -

awesome

Excellent job. There is way too much "mysticism" around neural networks. This shows clearly that for a classification problem all the nerual net is doing is creating a boundary function. Of course it gets complicated in multiple dimensions. But your explanations and use of graphs is excellent

what does x and y represent in the graph you use to show the cats and dog points ?

thx. subscribed

With ReLU f(x)=x is connect, f(x)=0 is disconnect. A ReLU net is a switched system of dot products, if that means anything to you.

Benefited a lot

thanks my man.

What are the axises on these graphs? Is it inputs, input*weights + bias for linear?

thanks brah

I've read at least three books on ANN's so far, but it's only now, after watching this video, that I have the intuition of what exactly is going on and how do activation functions break linearity!

so how do we know when to use relu or leacky relu? do we just use leacky relu all together in all cases?

What decides the shape of the boundary?

Amazing!!!!!!!!!!!!!!!!!

Awesome vid! Small sug: I might check the volume levels, during the screaming in :56 it was a bit painful to my ear and possibly sounded like audio clipping.

9:03 what do you mean "most neurons are off during the forward step"?

Lovely intro! I am learning at the age of 58!

but we cannot use ReLU for the regression of functions with high degrees of derivatives! In that case, we should still go with infinitely differentiable activation functions like "Tanh", right?

I've been trying to make a convolutional autoencoder for mnist, and at first I used sigmoid activation on the convolutional part and it couldn't make anything better than just a black screen on the output but when I removed all activation functions it worked well. Does anyone have any idea why that happened?

nice

So, we should always use leaky reLU

Great explanation. Just add more contrast to you color selection.

How is softmax a linear function here? Shouldn't it be non linear?

then why isn't leaky RELU ELU used everywhere in LSTM, GRU, Transformers ..? why is RELU used everywhere

What's the +1 node on each layer?

gr8 exp

1:16 I couldn't see that there were different colors so I was confused. Also I found the voicing of the training neural net annoying. But some people may like what other people dislike, so it's up to you to keep on voicing them.

gold, gold, gold.

good explanation but the noises are little bit annoying but thank you bro

Explained the Activation Function kzfaq.info/get/bejne/qceibNuaksfMZIE.html

followeeeed

👏👏👏❤️

wao! just wao

Swish: activation function. Swift: programming language. More homework, less sound effects 😀

I hate you for making that noises, i want to learn, comedia is something i would pass on

Perfect explanation!... Thanks

plot twist: its not that the boundary no longer changes, the vanishing gradient cause the gradient to be very small , that we can assume it is negligible

With graphical calculator, your explanation is sanely clear!! thank you!!

Thanks for the tutorial. I found the noises very cringe.

I still dont understand what a activation function is

learn Activation Functions with Dora but I honestly it is good

hahaha noice sounds

Wtf what's the sound of pictures...