![]() ![]() Let us assume from the below-given figure, we have a dataset that has X1 and X2 as independent features and Category as a dependent feature, sometimes we call it as target or label, So here for SVM, we will be using a term called HYPERPLANE, this plays important role in classifying the data into different groups (will see in detail very soon here in this article!). So now I hope we get some clarity w.r.t the dimensionality concept. Note: A point is a hyperplane in 1-dimensional space, a line is a hyperplane in 2-dimensional space, and a plane is a hyperplane in 3-dimensional space. Now we let that point move in another completely different direction and we have three dimensions. Three dimensions or 3-D – A-Solid (maybe a cube) We need two values to find a point on that plane.Ĥ. Now let us allow the point to move in a different direction. We need just one value to find a point on that line. ![]() Now let’s allow the point to move in one direction. One dimension or 1-D – A-line (with two points) No dimension or 0-D – A point (the only position exists)Ī point really has no size at all! But we show them as dots so we can see where they are!Ģ. Ex: Finding our mail between spam or not.ġ. ![]() Here, the dependent variable is a qualitative type like binary or multi-label types like yes or no, normal or abnormal, and categorical types like good, better, best, type 1 or type 2, or type 3. Classification: Finding a mapping function of the independent variable to identify discrete dependent variable, it can be labels or categories oriented. So, What is the term Classification and Regression?ġ. And in reality, the SVM algorithm comes under Supervised ML, and to the surprise, it deals with both Classification and Regression. Semi-Supervised Learning (Partial data’s with and without label)įrom the above content, it can be concluded that we are dealing with Supervised ML alone in this article. Reinforcement ML – This domain is something different the above two, here simple but complicated rule is learn by rewards and punishments (learning like kids in school)Ĥ. Again classified into Clustering, Anomaly Detection, Dimensionality reduction, Association rule-based learning.ģ. Unsupervised ML – Dataset/data having features alone or without target variables. It has two broad types: Classification and Regression.Ģ. Supervised ML – Dataset/data has features (independent variables) and target (dependent variable/target) variables. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |