SVM Kernal- Polynomial And RBF Implementation Using Sklearn- Machine Learning

Join Affordable ML and DL Course starting on April 10th
SVM Tutorials
All Playlist In My channel

Please donate if you want to support the channel through GPay UPID,

Please join as a member in my channel to get additional benefits like materials in Data Science, live streaming for Members and many more

Please do subscribe my other channel too

Connect with me here:

[vidhanjain]

I was not getting this topic but now you have given a very nice intuetion about SVM's in these 4 four videos.

[prateeksrivas]

hundred of articles summed up in one video and that too comprehensively. Great job. If someone watches these 4 video series on SVM, then I think he can confidently start mastering with at least 1 algorithm i.e., SVM. Brilliant stuff. Now I know what Mathematical concepts I need to polish further to apply and understand SVM further.

[lakhankumawat]

This is the most under rated video on svm topic on youtube..

[ajitkabadi]

Tq for all the videos sir, plz come up with more end to end projects with deployment it will be very helpful .

[rajkumarmaity]

Such a grate explanation i have ever seen at youtube. many many thanks sir for creating videos like this.

[cocoarecords]

Krish can you tell us how you learn new concepts very fast and manage to learn many things?

[Emotekofficial]

Krish thank you for this video. One question though, at 10:39 on line [219] why y is X1 Square? shouldn't it be X2 Square? Just wanted to be Clear.

[swarup]

fantastic video. I am not able to understand the complex concept of SVM. Its all thanks to your exception videos

[pushpitkumar]

Neat visualizations sir and as always explanation was up to the point. One question, shouldn't y be 'X2_sqaure' in the final plot?

[alfonsoortega]

Hi Krish. Congrats for your great job on clarifying all these difficult concepts... I have a comment on the way in which you decude the components of the linear kernel that will become the new features. You understand x^T y as a mattrix product between x^t (2x1 dimensions) and y (1x2 dimensions) resulting in the 2x2 dimension with the main components. Nevertheless, as far as I know x^T y should actually be interpreted as a product (scalar) product between a 1x2 mattrix and another 2x1 one resulting in the typical x1y1+x2y2. I have seen in other references that the polynomial kernel is in fact the dth power of the bynomion ( x^T y + 1) that in fact generates a polynomial whose terms are in fact a linear combination of the components you identify by means of the mattrix production interpretation... At this point, Im not sure if I am right or wrong.... could you clarify, please?

[ganeshrao]

Krish, just a suggestion can you put this after 85th SVM will be in series, earlier concepts clear till 85th continuing with this practical implementation will help for new ones who comes. I've repeated twice :).
if you can't explain it simply you, you don't understand it well enough - Einstein. you simplify it. Thank you

[ismailkaracakaya]

I think you need to change X1_Square to X2_Square below for y:
fig = px.scatter_3d(df, x='X1_Square', y='X2_Square', z='X1*X2',

[mallikasrivastava]

You are awesome I must say, I just pause the video and writing this.

[JohnAmose]

Simple and neat explanation. Thank you.

[minwin]

Hi when using the RBF classifier, is it possible to get the equation of the plane that it cuts? As I am interested in using that plane as a prediction to further values.

[Sahareajay]

Do data scientists work alone? How many data Scientist work in any organisation . why most of companies hire less Data scientist as compare to softwere Engineer.

[abhilashsingh]

You my good sir.... You're a genius :)

[AlokSingh-ijrw]

Please a video on data streaming with kafka

[cvb]

Hi Bro,
Can you please make a video on converting categorical values to numeric ?

[riddhidigital]

hi krish I just joined as member for data science material, from where i can get materials