Support Vector Machine Algorithm (SVM)
❖ SVMs are a supervised learning algorithm used for classification and regression problems.
❖ SVMs are primarily used for classification problems.
❖ The goal of SVMs is to create a hyperplane that separates data points into different classes.
❖ The hyperplane is chosen to maximize the margin between the two classes.
❖ Support vectors are the data points that are closest to the hyperplane.
Types of SVM
SVM can be of two types:
Linear SVM:
• For linearly separable data.
• Classifies using a straight line.
Non-Linear SVM:
• For non-linearly separable data.
• Uses complex curves for classification.
How Model Work:
Applications of SVM
➢ Face Detection: Classifies images of people's faces by creating a bounding box around them.
➢ Bioinformatics: Classifies genes to differentiate between proteins, identify biological
problems, and detect cancer cells.
➢ Text Categorization: Classifies documents into different categories based on their content.
➢ Generalized Predictive Control (GPC): Provides control over industrial processes.
➢ Handwriting Recognition: Recognizes handwritten characters by matching them against pre-
existing data.
➢ Image Classification: Classifies images into different categories.
Advantages of SVM
• It has a high level of accuracy
• It works very well with limited datasets
• Kernel SVM contains a non-linear transformation function to convert the
complicated non-linearly separable data into linearly separable data
• It is effective on datasets that have multiple features
• It is effective when the number of features are greater than the number of
data points
• It employs a subset of training points in the decision function or support
vectors, making SVM memory efficient
• Apart from common kernels, it is also possible to specify custom kernels for
the decision function
Disadvantages of SVM
• Does not work well with larger datasets
• Sometimes, training time with SVMs can be high
• If the number of features is significantly greater than the number of data
points, it is crucial to avoid overfitting when choosing kernel functions and
regularization terms
• Probability estimates are not directly provided by SVMs; rather, they are
calculated by using an expensive fivefold cross-validation
• It works best on small sample sets due to its high training time
