SVM(support vector Machine)withExplanation.pdf

SVM(support vector Machine)withExplanation.pdf

• 1.
  Support Vector Machine
• 2.
  • Support VectorMachine or SVM is one of the most popular Supervised Learning algorithms, • which is used for Classification as well as Regression problems. • However, primarily, it is used for Classification problems in Machine Learning. SVM
• 3.
  Prediction of SVM
• 4.
  Understanding SVM Confidence-building strategies
• 5.
  KEY TERMS • Hyperplane: •SVM identifies the optimal hyperplane that maximizes the margin between classes in the feature space. • Especially useful for scenario where linear separation is not feasible. • Support Vector Machine: • Support Vector are the data points closets to the hyperplane. • They play a pivotal role in determining the position and orientation of the optimal hyperplane.
• 6.
  Margin: Margin is distancefrom the decision surface to the closest data point Positive hyperplane + Negative Hyperplane=Margin Suppose D1+D2=M
• 7.
  GOAL The goal ofthe SVM algorithm is to create the best line or decision boundary that can segregate n dimensional space into classes so that we can easily put the new data point in the correct category in the future. This best decision boundary is called a hyperplane.
• 8.
  Types of SVM LinearSVM: Linear SVM is used for linearly separable data, which means if a dataset can be classified into two classes by using a single straight line, then such data is termed as linearly separable data, and classifier is used called as Linear SVM classifier.
• 9.
  Non-linear SVM Non-Linear SVMis used for non-linearly separated data, which means if a dataset cannot be classified by using a straight line, then such data is termed as nonlinear data and classifier used is called as Non-linear SVM classifier
• 10.
  Kernal Trick • SVMemploys the Kernal trick to handle no-linear relationships in data by mapping it into a higher dimensional space. • Enables SVM to capture complex patterns and make accurate prediction.
• 12.
  Drawback • Not suitablefor large datasets • Large training time • More features, more complexities • Bad performance on high noise • Choice of kernel • Computationally expensive