Machine Learning Machine Learning 2 — Questions and Answers
Question 1: Which regularization technique adds the sum of the absolute values of coefficients to the loss function?
- Ridge (L2)
- Lasso (L1) (Correct answer)
- Elastic Net
- Dropout
Correct answer: Lasso (L1)
Lasso (L1) regularization adds the sum of absolute coefficient values, which can shrink some coefficients to exactly zero, performing feature selection.
Question 2: In a confusion matrix, what does a False Negative represent?
- Model predicted positive and was correct
- Model predicted negative and was correct
- Model predicted positive but was wrong
- Model predicted negative but the true label was positive (Correct answer)
Correct answer: Model predicted negative but the true label was positive
A False Negative occurs when the model predicts the negative class but the true label is actually positive, meaning a positive case was missed.
Question 3: What is the purpose of the kernel trick in Support Vector Machines?
- To reduce the number of support vectors
- To map data into a higher-dimensional space without explicit computation (Correct answer)
- To speed up gradient descent
- To normalize input features automatically
Correct answer: To map data into a higher-dimensional space without explicit computation
The kernel trick allows SVMs to operate in high-dimensional feature spaces by computing dot products implicitly, enabling non-linear classification without explicit transformation.
Question 4: Which ensemble method trains models sequentially, each correcting errors of the previous one?
- Bagging
- Boosting (Correct answer)
- Stacking
- Voting
Correct answer: Boosting
Boosting trains weak learners sequentially, where each new model focuses on the errors made by the previous ensemble, reducing bias.
Question 5: What does the term 'epoch' mean in the context of neural network training?
- One forward pass through a single batch
- One complete pass through the entire training dataset (Correct answer)
- The learning rate schedule cycle
- The number of hidden layers
Correct answer: One complete pass through the entire training dataset
An epoch refers to one complete pass of the entire training dataset through the neural network during the training process.
Question 6: Which dimensionality reduction technique is unsupervised and maximizes variance in the projected space?
- Linear Discriminant Analysis (LDA)
- t-SNE
- Principal Component Analysis (PCA) (Correct answer)
- UMAP
Correct answer: Principal Component Analysis (PCA)
PCA is an unsupervised technique that finds orthogonal components that maximize the variance in the data, projecting it onto a lower-dimensional space.
Question 7: In k-means clustering, what is the objective function being minimized?
- Sum of distances between cluster centroids
- Within-cluster sum of squared distances to centroids (Correct answer)
- Between-cluster variance
- Silhouette score
Correct answer: Within-cluster sum of squared distances to centroids
K-means minimizes the within-cluster sum of squared distances (inertia), assigning each point to the nearest centroid and updating centroids iteratively.
Machine Learning Machine Learning 2
Which regularization technique adds the sum of the absolute values of coefficients to the loss function?