Machine Learning Fundamentals Flashcards
7 cards from real Data and Analytics practice questions. Tap to flip, then mark Knew It or Still Learning — missed cards come back until you master them.
Read the first 7 Machine Learning Fundamentals flashcards as text
Which type of machine learning involves training a model on labeled data to predict outcomes for new, unseen data?
Answer: Supervised learning
Supervised learning uses labeled training data where the correct output is known, allowing the model to learn mappings from inputs to outputs.
What is overfitting in a machine learning model?
Answer: The model learns training data too well and fails to generalize to new data
Overfitting occurs when a model memorizes training data noise and details, resulting in high training accuracy but poor performance on unseen data.
Which technique is used to prevent overfitting by adding a penalty term to the loss function?
Answer: Regularization
Regularization adds a penalty (L1 or L2) to the loss function to discourage the model from fitting noise and reduce overfitting.
In machine learning, what does the term 'feature engineering' refer to?
Answer: Transforming raw data into meaningful input variables for a model
Feature engineering is the process of using domain knowledge to create, transform, or select variables (features) from raw data to improve model performance.
What is the purpose of a validation set in machine learning?
Answer: To tune hyperparameters and select the best model during development
A validation set is used during model development to tune hyperparameters and compare different models, separate from the test set used for final evaluation.
Which of the following is an example of an unsupervised learning algorithm?
Answer: K-means clustering
K-means clustering is unsupervised because it groups data points based on similarity without using labeled training examples.
What does the bias-variance tradeoff describe in machine learning?
Answer: The balance between underfitting (high bias) and overfitting (high variance)
The bias-variance tradeoff describes how increasing model complexity reduces bias (underfitting) but increases variance (overfitting), requiring a balance for optimal generalization.