15:22 I think sir has quoted it wrong. For red points we find oil , since we have a tower above red points. and for blue points we don't find oil, since we don't have a tower above them.
How to learn the hight in the diagram using sigmoid neural? W - we will keep it high to make it work as a perceptron. B - it is used to shift the sigmoid neural. Then how this model will learn the height?
The weights of the hidden neurones are used for controlling the steepness of the sigmoid fun. And the bias is used for controlling the transformation point or the step point of the sigmoid fn. When the output of hidden neurone are added and controlling the weights and biases of this neurones appropriately we get a tower fn. Now we have to control the height of the tower fn. The height of the tower fn. is controlled by the weight of the output Neurone. Now the appropriate weights and biases of each neurones are learned by Gradient descend.
Theoretically it is possible based on the explanation given, but we are not using it in practice because a perceptron outputs either 0 or 1. Hence from probabilistic point of view it do not make sense. Watch previous videos if you have already recollect it
Sir, you are a maths artist!
salute to you sir please upload ml classes too
Logistic function is written wrong at 10:18, should have been +e instead of -e in the denominator.
Exactly! I was wondering the same...
I spent 10 mins on desmos thinking the same.
Need to watch again
Last video was one hell of a ride. Phew!!
Thank you, Great explanation!
Simply superb.
Superbly intuitive !!
wow amazing teacher.
universal approximation theorem: 3:10 (multilayer representation of sigmoid neurons)
15:22
I think sir has quoted it wrong.
For red points we find oil , since we have a tower above red points.
and for blue points we don't find oil, since we don't have a tower above them.
superb Mitesh sir
amazing
Dear Sir, You have uploaded an art. Please upload ML Classes also
could someone please explain what happens at 13:47 timestamp ? How come we add 1 and subtract 1 to get that tower ?
actually it is: multiply 1 to h11 and multiply -1 to h12 and now we add h11 and -h12 to get h21
How to learn the hight in the diagram using sigmoid neural?
W - we will keep it high to make it work as a perceptron.
B - it is used to shift the sigmoid neural.
Then how this model will learn the height?
The weights of the hidden neurones are used for controlling the steepness of the sigmoid fun. And the bias is used for controlling the transformation point or the step point of the sigmoid fn. When the output of hidden neurone are added and controlling the weights and biases of this neurones appropriately we get a tower fn. Now we have to control the height of the tower fn. The height of the tower fn. is controlled by the weight of the output Neurone. Now the appropriate weights and biases of each neurones are learned by Gradient descend.
Does this also mean that we can as well use a network of perceptrons in place of sigmoids to approximate any continuous function?
Theoretically it is possible based on the explanation given, but we are not using it in practice because a perceptron outputs either 0 or 1. Hence from probabilistic point of view it do not make sense. Watch previous videos if you have already recollect it
In reality you cant use a step function because the weights are calculated by backpropagation and you cannot backpropagate through a step function
No! because step function is not continuous and thus you cannot find derivative of final loss function with respect to parameters.
Anyone mind providing the link professor is referring to?
Didn’t understand anything a single penny the way of teaching is worse than our teacher kanji❤️
True
Do we need 2*n number of neurons in case of n dimensions ? Can someone correct this please ?
true
Sir, I have a doubt. Instead of making tower function from two step function, can we approximate it using other functions, such as gaussian?
Yes you can. People use Relu or Tanh instead of step functon which is not diferentialbe at 0, whereas ReLu is.
Shouldn't the 3D tower retain only those values greater than or equal to 2?
The threshold is set at >= 1, so if you observe closely, we are also counting the base of the tower as well
Logistic function is written wrong at 10:18, should have been +e instead of -e in the denominator.