Given that a linear SVM classifier uses a hyperplane that is derived from the equation of a line y=wx+b. When performing linear classification, do we consider the weight, w, and bias, b, as internal parameters to the classifier or there is an option to set them for optimal performance?
Classification is basically an optimization problem, which can be conducted via input to output representation model/function/algorithm/method, where the performance may be based on several aspects of the given data, model/method and way of nonparametric clustering for classification. For comprehensive understanding of such phenomenon and other principals of classification, I would like to suggest you to read the attached book.
choose any values for your adjustable parameters using image processing software such as ENVI .
https://medium.com/usf-msds/deep-learning-best-practices-1-weight-initialization-14e5c0295b94
- Badges
- Science topic