I always prefer reading books rather than watching YT videos. Because content in YT videos despite being easy to understand is always incomplete. But in your case not only content is super easy to understand but also much more in-depth and with a lot of practical advices than many books. Hope you get time and upload lectures on Kernel Mathematics and other topics which you mentioned in this last video.
I studied SVM by a paid instructor and he made it so desirably scary that even to think of applying SVM in real world scenarios haunts me. But after going thru your SVM playlist I have got the intuition and mathematics how it works and also the soft margin classifier was never understood by me of what was that zeeta actually.
@campus_x sir does the kernel also check for the width of the curve or just the position of the curve , what if the spread of the inner class is more and we need more area than what e^-x**2 is offering us ,like you have said that i checks at every landmark and calculates the accuracy measure And even the plot after you have used rbf kernel ,it is closer to blue points , it is not satisfying the condition of maximizing the distance between 2 classes or support vectors
How to visualize a kernel SVM classification model with three input, I mean How can we plot 3 Dimensional plot for the SVM classification model? and when we have more than two input variables how to visualize on a graph or it is not possible to do that?
I usually dont hit like on any videos, but can't resist with ur videos
I always prefer reading books rather than watching YT videos. Because content in YT videos despite being easy to understand is always incomplete.
But in your case not only content is super easy to understand but also much more in-depth and with a lot of practical advices than many books.
Hope you get time and upload lectures on Kernel Mathematics and other topics which you mentioned in this last video.
couldn't' agree more
Can you prefere which book you are reading for ml? I'm begginer so it would help if you tell me. 🙂
@@princekhunt1 Go for "Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow".
@@princekhunt1 hands on machine learning by Geron
The best explanation of Support vector machine with math and geometric intuition
Jo SVM whole sem ni aaya smjh vo exam se ek raat phle 2 hours mai aa gaya thank a lot sirr
I studied SVM by a paid instructor and he made it so desirably scary that even to think of applying SVM in real world scenarios haunts me. But after going thru your SVM playlist I have got the intuition and mathematics how it works and also the soft margin classifier was never understood by me of what was that zeeta actually.
absolutely awesome playlist for SVM, specially to understand the whole working of thing
We live in a world where teacher like nitish sir is underrated
your teaching is a work of art
Best I mean nobody on youtube gas explained like this.
Hi Nitish, Will you add any further video on Kernel Mathematics? as you mentioned in this last video
did u get that videos so please help where did u cover that all ?
great playlist , the best one i have watched. thnx for the great videos.
@campus_x sir does the kernel also check for the width of the curve or just the position of the curve , what if the spread of the inner class is more and we need more area than what e^-x**2 is offering us ,like you have said that i checks at every landmark and calculates the accuracy measure
And even the plot after you have used rbf kernel ,it is closer to blue points , it is not satisfying the condition of maximizing the distance between 2 classes or support vectors
Thank you for sharing your knowledge!
Very well explained
Thank you Nitish bhai!!
Wait, rbf kernel - does it create a circular decision boundary or it creates a linear plane after internal data transformations?
it is creating flat plane, but the image we are watching is 2d, hence from top view it is looking like circle.
Can also plot feature importance plot for it??
can you upload a video on kernel mathematics?
thank you
First I like then I watch.
How to visualize a kernel SVM classification model with three input, I mean How can we plot 3 Dimensional plot for the SVM classification model? and when we have more than two input variables how to visualize on a graph or it is not possible to do that?
Need videos on kernel mathematics pleaseeeee
nice explanation sir
Thank You Sir.
sir continue with video's
ThankYou Sir
sir ji thoda RBF wagera bhi padha do time nikal kr . Ur kripa on me . thanks!
Your have used sample_generator in your code which is deprecated and not supported in python!! But theoretically you have explained well.
from sklearn.datasets import make_circles
X, y = make_circles(100, factor=.1, noise=.1)
plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='bwr')
plt.show()
This code will work..
finished watching
Thanks Sir...
thnx a lot man
but why transformation is valid on data? ...i mean we changing the original values so it will affect on predication
Thank you very much
nice video
YE BHAI TO KAMAL hai
great
bro ily!
---------------------------------------------------------------------------
ModuleNotFoundError Traceback (most recent call last)
Cell In[6], line 1
----> 1 from sklearn.datasets.samples_generator import make_circles
2 X, y = make_circles(100, factor=.1, noise=.1)
4 plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='bwr')
ModuleNotFoundError: No module named 'sklearn.datasets.samples_generator'
error bro
use : from sklearn.datasets import make_circles
have you imported the scikitlearn package ?
from sklearn.datasets import make_circles
from sklearn.datasets import make_circles
X, y = make_circles(100, factor=.1, noise=.1)
plt.scatter(X[:, 0], X[:, 1], c=y, s=50, cmap='bwr')
plt.show()