Hi, how did you decide that the Ф function should be 6-x1.. etc.? And why is the square root in the condition? I understand that the points in the blue class lie on the circle x1^2 + x2^2 = 2 since the radius of this circle is the square root of 2. Yet, I can't figure out how did you get the Ф function.
+Unwritten48 have you found it? If you haven't found it try to search more about kernel trick. nlp.stanford.edu/IR-book/html/htmledition/nonlinear-svms-1.html
sir wonderfull expalnation. can you please take one example of coordinates and how the linear,polynomial and gaussian kernels are working to classify the proble.
How did you choose the mapping function? What about Kernel Tricks? What are those and how are they incorporated in this video? This video is good but is so customized is kinda useless to people trying to learn non-linear SVM.
Hi sir, Thank you for making life easy. I have two questions if u don't mind: is the formula 6- x1+(x1-x2) greater or equal to 2 fixed? i.e. in our example, the read points make a boundary of max 2. Is that the reason you chose greater or equal to 2 or this is a fixed equation regardless of the coordinates of the points?
Thanks. It eases out the terminology kernel, Lagrangian multiplier, vector algebra, etc. It the procedure appears to be working on trivial cases. I've tried with few points but it doesn't seem to be yielding correct results.
and please can you show in libsvm how training and testing of data is done and how to fine support vector if there are many data in this we can easily guess the support vector but if data is too big then how do we guess the support vectors
Hi, how did you decide that the Ф function should be 6-x1.. etc.? And why is the square root in the condition?
I understand that the points in the blue class lie on the circle x1^2 + x2^2 = 2 since the radius of this circle is the square root of 2. Yet, I can't figure out how did you get the Ф function.
+Unwritten48 have you found it? If you haven't found it try to search more about kernel trick. nlp.stanford.edu/IR-book/html/htmledition/nonlinear-svms-1.html
Hi Ary. Could explain, with an example elaborating the video explaination on how 6 is found?
sir wonderfull expalnation. can you please take one example of coordinates and how the linear,polynomial and gaussian kernels are working to classify the proble.
Thank you very much.... It is so helpful.
simple and clear.
How did you choose the mapping function? What about Kernel Tricks? What are those and how are they incorporated in this video? This video is good but is so customized is kinda useless to people trying to learn non-linear SVM.
Hi sir,
Thank you for making life easy.
I have two questions if u don't mind:
is the formula 6- x1+(x1-x2) greater or equal to 2 fixed? i.e. in our example, the read points make a boundary of max 2. Is that the reason you chose greater or equal to 2 or this is a fixed equation regardless of the coordinates of the points?
pls make a video of how you derived the mapping function
Thanks. It eases out the terminology kernel, Lagrangian multiplier, vector algebra, etc. It the procedure appears to be working on trivial cases. I've tried with few points but it doesn't seem to be yielding correct results.
Thank you Sir. One thing, how to choose the mapping function ???
I think once we find the support vectors, we again need to apply the Ф function on it and then use in the equations. Is that the case??
This is really nice.. Very well explained!!
sir why you have taken value 0.0859 during multiplication because actual value is 0.859
how you define your map function?
Awesome to understand SVM
Great tutorial. Well done!
what does alpha1, alpha2, alpha3 signifies? what is it used for?
and please can you show in libsvm how training and testing of data is done and how to fine support vector if there are many data in this we can easily guess the support vector but if data is too big then how do we guess the support vectors
From where the 6 comes?
how do we come to know which one are the support vectors if there are so many points in the datasets
really how? I also ask like your question
Nice work.
Very nice. Thanks!
it good and understanble
Many thanks
EXCELLENT!
Thank you.