1. Which of the following is a subfield of Artificial Intelligence?
A. Quantum Computing
B. Neural Networks
C. Data Science
D. Web Development
Answer: b) Neural Networks
Rationale: Neural networks are a subfield of AI that is modeled after the human brain
to simulate learning and decision-making processes.
2. What is the purpose of backpropagation in neural networks?
A. To initialize weights randomly
B. To optimize the model's loss function by adjusting weights
C. To evaluate the model's performance
D. To avoid overfitting
Answer: b) To optimize the model's loss function by adjusting weights
Rationale: Backpropagation is a method for updating the weights in a neural network
by calculating the gradient of the loss function with respect to each weight.
,3. In which phase does a machine learning model evaluate its performance using data
that it hasn’t seen before?
A. Training
B. Testing
C. Validation
D. Deployment
Answer: b) Testing
Rationale: Testing evaluates a model's performance on unseen data to ensure it
generalizes well.
4. What does "feature extraction" mean in machine learning?
A. Selecting important features from the dataset
B. Reducing the size of the dataset
C. Generating new features from raw data
D. None of the above
Answer: c) Generating new features from raw data
Rationale: Feature extraction involves transforming raw data into more useful features
that the model can use for learning.
, 5. In a neural network, what is the role of an activation function?
A. It adjusts the learning rate during training
B. It introduces non-linearity to the model
C. It calculates the model’s loss
D. It increases the number of layers in the network
Answer: b) It introduces non-linearity to the model
Rationale: The activation function helps the neural network model complex patterns
by introducing non-linearities, allowing it to learn from data more effectively.
6. In machine learning, what does "bias" refer to?
A. The difference between the predicted value and the true value
B. A hyperparameter of the model
C. The inclination of the model to make certain assumptions or predictions
D. The method of regularization used in the model
Answer: c) The inclination of the model to make certain assumptions or predictions
Rationale: Bias refers to the model’s tendency to make predictions that systematically
differ from the true values, often due to assumptions or oversimplifications in the
model.
A. Quantum Computing
B. Neural Networks
C. Data Science
D. Web Development
Answer: b) Neural Networks
Rationale: Neural networks are a subfield of AI that is modeled after the human brain
to simulate learning and decision-making processes.
2. What is the purpose of backpropagation in neural networks?
A. To initialize weights randomly
B. To optimize the model's loss function by adjusting weights
C. To evaluate the model's performance
D. To avoid overfitting
Answer: b) To optimize the model's loss function by adjusting weights
Rationale: Backpropagation is a method for updating the weights in a neural network
by calculating the gradient of the loss function with respect to each weight.
,3. In which phase does a machine learning model evaluate its performance using data
that it hasn’t seen before?
A. Training
B. Testing
C. Validation
D. Deployment
Answer: b) Testing
Rationale: Testing evaluates a model's performance on unseen data to ensure it
generalizes well.
4. What does "feature extraction" mean in machine learning?
A. Selecting important features from the dataset
B. Reducing the size of the dataset
C. Generating new features from raw data
D. None of the above
Answer: c) Generating new features from raw data
Rationale: Feature extraction involves transforming raw data into more useful features
that the model can use for learning.
, 5. In a neural network, what is the role of an activation function?
A. It adjusts the learning rate during training
B. It introduces non-linearity to the model
C. It calculates the model’s loss
D. It increases the number of layers in the network
Answer: b) It introduces non-linearity to the model
Rationale: The activation function helps the neural network model complex patterns
by introducing non-linearities, allowing it to learn from data more effectively.
6. In machine learning, what does "bias" refer to?
A. The difference between the predicted value and the true value
B. A hyperparameter of the model
C. The inclination of the model to make certain assumptions or predictions
D. The method of regularization used in the model
Answer: c) The inclination of the model to make certain assumptions or predictions
Rationale: Bias refers to the model’s tendency to make predictions that systematically
differ from the true values, often due to assumptions or oversimplifications in the
model.
