# Introduction to Computer Vision and Image Processing Week 3

Course Name: Introduction to Computer Vision and Image Processing

Course Link: Introduction to Computer Vision and Image Processing

### Practice Assessment

Q1. You select the learning rate
Using the validation data
The learning rate should always be one
Randomly

Q2. Support Vector Machines for Image classification may use kernels. There are different types of Kernels, which of the following is not a type of Kernel?
Polynomial
Linear

Q3. The difference between Logistic Regression and Softmax is
Softmax is used for Multi-class Classification
only Logistic Regression has probabilistic outputs
they are the same

Answer: Softmax is used for Multi-class Classification

These are answers of Introduction to Computer Vision and Image Processing Week 3 Quiz

Q4. Other methods  to convert a two-class classifier to multiclass classifier they include
One-vs-rest
One-vs-one
support vector machines (SVM)

Q5. What methods can you use for Multiclass classification with no alteration
Logistic Regression
k-nearest neighbors
Support Vector Machines
Softmax

These are answers of Introduction to Computer Vision and Image Processing Week 3 Quiz

Q1. You train a Support Vector Machine and obtain an accuracy of 100% on the training data and 50% on the validation data. This is an example of:
Overfitting
Underfitting
A good model

Q2. When dealing with image classification, what kind of challenges do we face with images?
Variations due to scaling
Variations due to illumination
Image occlusion.
All of the above

These are answers of Introduction to Computer Vision and Image Processing Week 3 Quiz

Q3. Support Vector Machines for Image classification may use a kernels. There are different types of Kernels, which of the following is not a type of Kernel?
Linear
Polynomial

Q4. In a sequence of array, what does the argmax function return?
It will return 0
The sequence of array in ascending order
The index corresponding to the minimum value
The index corresponding to the maximum value

Answer: The index corresponding to the maximum value

Q5. You train a Support Vector Machine with a RBF kernel and obtain an accuracy of 100% on the training data and 50% on the validation data. What should you do to the parameter Gamma?
Increase Gamma
Decrease Gamma
Leave Gamma unchanged