Feature Scaling
Feature scaling is a data preprocessing technique used to standardize the range of independent variables (features) in a dataset. Techniques like normalization (scaling to a 0-1 range) or standardization (scaling to a mean of 0 and standard deviation of 1) prevent features with larger numerical values from disproportionately influencing model training. This is especially important for algorithms that rely on distance calculations or gradient descent.
Think of it like putting all ingredients in a recipe into common units, such as grams, instead of some being in cups, some in ounces, and some in pinches, to ensure accurate proportions.
Proper feature scaling improves the convergence speed of many machine learning algorithms and can significantly impact a model's performance and stability.
Learn one new AI thing every day.
Daily Deck sends you seven plain-English cards like this every morning. Free.
Start free