1. Which of the following algorithms is used for both regression and classification
problems?
A. Support Vector Machine (SVM)
B. K-means
C. Naive Bayes
D. Random Forest
Answer: d) Random Forest
Rationale: Random Forest can be used for both regression (predicting continuous
values) and classification (predicting discrete values) tasks.
2. Which of the following is NOT a type of neural network architecture?
A. Convolutional Neural Networks (CNN)
B. Recurrent Neural Networks (RNN)
C. Naive Bayes
D. Feedforward Neural Networks (FNN)
Answer: c) Naive Bayes
,Rationale: Naive Bayes is a probabilistic classifier, not a type of neural network
architecture.
3. What does the term "bias" refer to in the context of machine learning models?
A. The complexity of the model
B. The error due to overly simplistic assumptions in the model
C. The error from incorrect input data
D. The ability of the model to learn from data
Answer: b) The error due to overly simplistic assumptions in the model
Rationale: Bias refers to systematic errors that arise when a model makes assumptions
that simplify the learning process but might lead to inaccuracies.
4. What is the purpose of the "softmax" activation function?
A. To introduce non-linearity into the model
B. To normalize the output of a neural network to represent probabilities
C. To reduce the loss function
D. To prevent overfitting
Answer: b) To normalize the output of a neural network to represent probabilities
, Rationale: Softmax converts raw output scores into probabilities, ensuring that the
sum of the outputs for each class is 1, which is particularly useful for multi-class
classification.
5. Which of the following techniques can be used for dimensionality reduction?
A. K-nearest neighbors
B. Principal Component Analysis (PCA)
C. Decision Trees
D. Logistic Regression
Answer: b) Principal Component Analysis (PCA)
Rationale: PCA is a method for reducing the number of features in a dataset while
preserving as much variance as possible, making it an effective technique for
dimensionality reduction.
6. Which of the following is a method to deal with overfitting?
A. Decrease the size of the dataset
B. Use a simpler model
C. Increase the learning rate
D. Use more features
problems?
A. Support Vector Machine (SVM)
B. K-means
C. Naive Bayes
D. Random Forest
Answer: d) Random Forest
Rationale: Random Forest can be used for both regression (predicting continuous
values) and classification (predicting discrete values) tasks.
2. Which of the following is NOT a type of neural network architecture?
A. Convolutional Neural Networks (CNN)
B. Recurrent Neural Networks (RNN)
C. Naive Bayes
D. Feedforward Neural Networks (FNN)
Answer: c) Naive Bayes
,Rationale: Naive Bayes is a probabilistic classifier, not a type of neural network
architecture.
3. What does the term "bias" refer to in the context of machine learning models?
A. The complexity of the model
B. The error due to overly simplistic assumptions in the model
C. The error from incorrect input data
D. The ability of the model to learn from data
Answer: b) The error due to overly simplistic assumptions in the model
Rationale: Bias refers to systematic errors that arise when a model makes assumptions
that simplify the learning process but might lead to inaccuracies.
4. What is the purpose of the "softmax" activation function?
A. To introduce non-linearity into the model
B. To normalize the output of a neural network to represent probabilities
C. To reduce the loss function
D. To prevent overfitting
Answer: b) To normalize the output of a neural network to represent probabilities
, Rationale: Softmax converts raw output scores into probabilities, ensuring that the
sum of the outputs for each class is 1, which is particularly useful for multi-class
classification.
5. Which of the following techniques can be used for dimensionality reduction?
A. K-nearest neighbors
B. Principal Component Analysis (PCA)
C. Decision Trees
D. Logistic Regression
Answer: b) Principal Component Analysis (PCA)
Rationale: PCA is a method for reducing the number of features in a dataset while
preserving as much variance as possible, making it an effective technique for
dimensionality reduction.
6. Which of the following is a method to deal with overfitting?
A. Decrease the size of the dataset
B. Use a simpler model
C. Increase the learning rate
D. Use more features
