The lack of support in Support Vector
These past few days have been a complete drag. I wanted to get through with the support vector regression module, but even after watching the video three times, it made zero sense to me. It felt like it was time to take out the big guns.
The first step I took in this direction was finding the right blogs and videos. I found this video on youtube: https://www.youtube.com/watch?v=Y6RRHw9uN9o. This was a great help, especially the comic timing of the speaker keeps you hooked. I feel that it got a little overwhelming watching the same videos over and over again. I also fished out my old notes from last semester. Spent a whole day trying to figure out what I studied back then.
Learning on your own is not a smooth sailing ever. It's a pretty rocky boat. You never know where will you get stuck and for how long. And as the topics get more and more complicated I could feel the frustration creeping in. I thought it might be a good time to take day or two off and gather my bearings on the subject. Maybe going back to the text would give me some ideas.
I thought I might even want to go the Introduction to Statistical Learning book I studied last semester. I had a solid understanding of the support vector system and how the hyperplane works but it's the application of this concept in Regression that I could not wrap my brain around.
More google search lead me to this topic on stack overflow: https://stats.stackexchange.com/questions/82044/how-does-support-vector-regression-work-intuitively
This page had the discussion I needed all along. I hope this will help me compile everything in a precise way on next blog entry!
Fingers Crossed!!
The first step I took in this direction was finding the right blogs and videos. I found this video on youtube: https://www.youtube.com/watch?v=Y6RRHw9uN9o. This was a great help, especially the comic timing of the speaker keeps you hooked. I feel that it got a little overwhelming watching the same videos over and over again. I also fished out my old notes from last semester. Spent a whole day trying to figure out what I studied back then.
Learning on your own is not a smooth sailing ever. It's a pretty rocky boat. You never know where will you get stuck and for how long. And as the topics get more and more complicated I could feel the frustration creeping in. I thought it might be a good time to take day or two off and gather my bearings on the subject. Maybe going back to the text would give me some ideas.
I thought I might even want to go the Introduction to Statistical Learning book I studied last semester. I had a solid understanding of the support vector system and how the hyperplane works but it's the application of this concept in Regression that I could not wrap my brain around.
More google search lead me to this topic on stack overflow: https://stats.stackexchange.com/questions/82044/how-does-support-vector-regression-work-intuitively
This page had the discussion I needed all along. I hope this will help me compile everything in a precise way on next blog entry!
Fingers Crossed!!
Comments
Post a Comment