Machine Learning & Algorithms Flashcards

What is the difference between supervised and unsupervised learning?

Answer: Supervised learning uses labeled data, unsupervised learning uses unlabeled data

The core distinction between supervised and unsupervised learning lies in the presence of labels in the training data. Supervised learning algorithms learn from data where each input is paired with a correct output label, enabling them to make predictions on new data. In contrast, unsupervised learning algorithms work with unlabeled data to discover hidden structures, patterns, or groupings without any prior knowledge of output categories.

Which machine learning algorithm is used for classification tasks?

Answer: Logistic regression

Logistic regression is a statistical model primarily used for binary classification tasks, predicting the probability of an outcome belonging to one of two classes. It employs a sigmoid function to map predictions to probabilities between 0 and 1, making it ideal for categorizing data points into distinct groups. Unlike linear regression, which predicts continuous values, logistic regression is specifically designed for categorical outcomes.

What is the purpose of decision trees in machine learning?

Answer: To classify data based on input features

Decision trees are supervised machine learning algorithms primarily used for classification tasks, though they can also handle regression. They work by creating a model that predicts the value of a target variable by learning simple decision rules inferred from the data features. The tree structure allows for a clear, interpretable path to classify data points into specific categories based on a series of questions about their attributes.

Why is cross-validation used in machine learning?

Answer: To evaluate model performance and avoid overfitting

Cross-validation is a resampling procedure used to evaluate machine learning models on a limited data sample. Its primary purpose is to assess how well a model generalizes to an independent dataset and to detect or prevent overfitting. By partitioning data into multiple folds for training and testing, it provides a more robust estimate of model performance than a single train-test split.

What is the purpose of gradient descent in machine learning?

Answer: To minimize the loss function by updating model parameters

Gradient descent is an optimization algorithm used to minimize the loss function of a model by iteratively adjusting its parameters (weights and biases). It calculates the gradient of the loss function with respect to each parameter and moves in the direction opposite to the gradient, effectively finding the steepest path downwards. This iterative process helps the model converge to the optimal set of parameters that yield the lowest prediction error.

What is the function of support vector machines in machine learning?

Answer: To separate data into distinct classes using hyperplanes

Support Vector Machines (SVMs) are powerful supervised learning models primarily used for classification tasks. Their core function is to find an optimal hyperplane that distinctly separates data points belonging to different classes in a high-dimensional space. The goal is to maximize the margin between the classes, which improves the model's generalization ability to new, unseen data.

What is overfitting in machine learning?

Answer: When a model performs well on training data but poorly on new data

Overfitting occurs when a machine learning model learns the training data too well, capturing noise and specific patterns that are not representative of the underlying data distribution. This results in the model performing exceptionally well on the data it was trained on but failing to generalize effectively to new, unseen data. Consequently, its predictive accuracy on real-world scenarios becomes significantly lower.

Why is data preprocessing important in machine learning?

Answer: To normalize, clean, and transform data to improve model performance

Data preprocessing is a crucial step in machine learning that involves cleaning, transforming, and integrating raw data into a suitable format for model training. This includes handling missing values, normalizing or scaling features, and encoding categorical variables. Proper preprocessing ensures data quality, reduces noise, and helps models learn more effectively, leading to improved accuracy and performance.

What is ensemble learning in machine learning?

Answer: Combining multiple models to improve performance

Ensemble learning is a technique that combines predictions from multiple individual machine learning models (often called 'weak learners') to achieve better predictive performance than any single model alone. By aggregating diverse models, ensemble methods like Random Forests, Bagging, and Boosting can reduce bias and variance, leading to more robust and accurate predictions. This approach leverages the 'wisdom of crowds' to enhance overall model reliability.