Selected MCQ

Current Question
What does "CNN" typically stand for in machine learning?
  • A. Circular Neural Network
  • B. Convolutional Neural Network
  • C. Cascaded Neural Net
  • D. Cluster Network Model
Correct Answer: B
Explanation:
CNN stands for Convolutional Neural Network, often used in image processing tasks.
Related Question 1
What is 'ensemble learning' in machine learning?
  • A. Training deep networks only
  • B. Combining predictions of multiple models
  • C. Feature scaling process
  • D. A single-model hyperparameter search
Correct Answer: B
Explanation:
Ensemble learning combines predictions from several models to improve overall performance.
Related Question 2
Which algorithm is best suited for classification tasks in machine learning?
  • A. Linear regression
  • B. K-means
  • C. Support vector machine
  • D. PCA
Correct Answer: C
Explanation:
Support Vector Machine is commonly used for classification problems.
Related Question 3
In machine learning, what is 'dropout'?
  • A. Dropping the dataset
  • B. Randomly omitting neurons during training
  • C. Pruning decision trees
  • D. Deleting old data
Correct Answer: B
Explanation:
Dropout is a regularization technique in which random neurons are randomly deactivated during training to prevent overfitting.
Related Question 4
What is the purpose of an epoch in machine learning training?
  • A. A type of activation function
  • B. A full pass through the entire training dataset
  • C. A regularization technique
  • D. A specific type of loss function
Correct Answer: B
Explanation:
One epoch means the learning algorithm has processed the entire training dataset once.
Related Question 5
In machine learning, what does "overfitting" refer to?
  • A. The model performs well on training data but poorly on new data
  • B. Model generalizes well to unseen data
  • C. Insufficient training iterations
  • D. A data normalization technique
Correct Answer: A
Explanation:
Overfitting means the model has learned noise or specific patterns of training data and fails to generalize to new data.