Activation Functions - EXPLAINED!
Вставка
- Опубліковано 3 жов 2024
- We start with the whats/whys/hows. Then delve into details (math) with examples.
Follow me on M E D I U M: towardsdatasci...
REFERENCES
[1] Amazing discussion on the "dying relu problem": www.quora.com/...
[2] Saturating functions that "squeeze" inputs: stats.stackexc...
[3] Plot math functions beautifully with desmos: www.desmos.com/
[4] The paper on Exponential Linear units (ELU): arxiv.org/abs/...
[5] Relatively new activation function (swish): arxiv.org/pdf/...
[6] Used an Image of activation functions from this Pawan Jain's Blog: towardsdatasci...
[7] Why bias in Neural Networks? stackoverflow....
the screetching noise is irrtitaing..else nice tutoial
I agree
agreed. cringe and irritating
I don't agree
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 :)
No, dropout is different. Random sets of neurons are turned off in order to cause the neurons to form redundancies which can make the model more robust. In the case of dying Relu, the same neurons are always dead, making them useless. Dropout is desirable and deliberate, dying Relu is not.
Straight to the point. Nice and super clean explanation for non-linear activation functions. Thanks!
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.
Anytime :)
The most thing I love about your videos is the fun you add... Learning becomes a bit easier
One of the best explanations ive come across
I hate you for making that noises, i want to learn, comedia is something i would pass on
I discovered your page just yesterday and might I say, YOU'RE AWESOME! Thanks for such good content bro.
Thanks homie! Will dish out more soon!
Amazing! Finally I am able to visualise vanishing gradient descent and dying relu.
Glad!
best explanation of activation functions I ever seen
Great explanation ! and the animations with maths formula and visualizing it is awesome !! Many thanks !
7:48 "once it hits zero the neuron becomes useless and there is no learning" this explains so much, thank you!
Wooo, Did I just noticed the complex explained simple. Thanks! Looking forward to more videos.
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 !
Haha. Glad the references are useful! :)
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.. 😄
Thank you. I'm always thinking of more content :)
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
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?
It means that sigmoid function will always output a value between 0 and 1 regardless of any real number input. Notice the mathematical formula and graph of a sigmoid function for better clarity. Any real number will be converted to a number between 0 and 1. Hence sigmoid is said to "squeeze" values.
better than most professors, thanks for great video
Thanks!!
wonderful explanation!!!
Can you cover tanh activation? (Thanks for making this one so good!)
I wonder if there is enough support that warrants a video on just tanh. Will look into it though! And thanks for the compliments :)
Thank you very much for the great, and smooth explanation. This was really perfect.
Much appreciated Malek! Thanks for watching!
great .. so many thanks ... need more explanation
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.
Thank you for sharing! This video cleared my doubts and gave me a good introduction to learn
further
Super glad :)
good explanation for a beginner
Amazing presentation ,easy and captivating to grasp
Glad you liked it! Thank you!
Excellent explanation. Thank you.
wow, that was really helpful, thanks a ton!!!!
Glad to hear that. Thanks for watching!
oh man, amazing explanation.Thanks
Beautiful explanation!
Great explanation for activation function I like it so much
Thanks so much for commenting
THIS HELPED SO MUCH! THANK YOU!
What are the axises on these graphs? Is it inputs, input*weights + bias for linear?
did you get answer for it?
then why isn't leaky RELU ELU used everywhere in LSTM, GRU, Transformers ..? why is RELU used everywhere
Great explanation! Had to switch to earphones though :P
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.
Really awesome video!
Lovely intro! I am learning at the age of 58!
What I was looking for. Thanks!
Another great video
🎉🎉🎉!
Thanks so much!
That's great explanation
Thanks so much for watching !
Nicely explained
Thanks for watching this too
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
9:03 what do you mean "most neurons are off during the forward step"?
This was really helpful! Thanks!
Thanks for watching :)
How is softmax a linear function here? Shouldn't it be non linear?
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!
This was an amazing video!!! Keep up the good work!
Thanks so much!
this guy is genius
So, we should always use leaky reLU
really helpful..thanks
With graphical calculator, your explanation is sanely clear!! thank you!!
Thanks so much for the kind comment! Glad the strategy of explaining is useful :)
Great video, keep going !
what does x and y represent in the graph you use to show the cats and dog points ?
Amazing explanation and also funny 😅👏👏👏
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.
the dude is making these videos alone, if you don't like his voice that's on you, but he can't just change his voice
good explanation but the noises are little bit annoying but thank you bro
thank you very much, this is really helpful
Thanks:)
Great explanation. Just add more contrast to you color selection.
My palette is rather bland i admit
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?
Awesome video man !
awesome video
Thanks for the tutorial. I found the noises very cringe.
What decides the shape of the boundary?
Thanks mate
so how do we know when to use relu or leacky relu? do we just use leacky relu all together in all cases?
gold, gold, gold.
good work bro keep it up
-
Will do homie
awesome
Great Video and great page :) Which softwares you use to make these videos ?
Thanks! I use Camtasia Studio for the editing; Photoshop and draw.io for the images.
Thanks man)
it should be possible to let (part of) the net optimize its own activation function no?
Amazing!
I still dont understand what a activation function is
Benefited a lot
Awesome! Glad!
good job thank you
Very welcome!
@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?
6:45 - The line corresponds to those points in the feature space (the 2 feature values) where The sigmoid's height is 0.5.
can we use linear activation with hinge loss for Linear svm for binary classification.
Quality video!
yes! I liked it. Keep it up.
Swish: activation function. Swift: programming language. More homework, less sound effects 😀
Nice catch. I misspoke :)
this is helpful, thanks :)
thanks brah
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
Danana nanana nanana nana
I don't understand..
thanks my man.
You are oh so welcome
learn Activation Functions with Dora
but I honestly it is good
Bhai video shayad accha hoga but thumbnail pe Teri pic dekhke hi kafi log click na kare, I'm here just to let you know this:avoid putting your face on thumbnail or in video as no one is interested in seeing the educator while watching technical videos.
You clicked. That's all i care about ;)
Amazing!!!!!!!!!!!!!!!!!
Thanks!!!!!!!!!!
Perfect explanation!... Thanks
Much appreciated!
thx. subscribed
What's the +1 node on each layer?
The bias term
gr8 exp
Thank you. Really appreciate it
followeeeed
Replieeeeed. Thanks!
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?
Are the outputs properly scaled back to pixel values after being squeezed by sigmoid?
@@fatgnome Yes. Otherwise the output wouldn't match with images. Also I checked model.summary() every time I made changes to the model.
nice
Explained the Activation Function ua-cam.com/video/sar9xi-ah4M/v-deo.html
Wtf what's the sound of pictures...
👏👏👏❤️