Did you know that

machine Learning | Google for devlopers.google.com/machine-learning Machine Learning Foundational courses New Machine Learning Crash Course A hands-on course to explore the critical basics of machine learning. Linear Regression An introduction to linear regression, covering linear models, loss, gradient descent, and hyperparameter tuning. Logistic Regression An introduction to logistic regression, where ML models are designed to predict the probability of a given outcome. Classification An introduction to binary classification models, covering thresholding, confusion matrices, and metrics like accuracy, precision, recall, and AUC. Working with Categorical Data Learn the fundamentals of working with categorical data: how to distinguish categorical data from numerically using one-hot encoding, feature hashing, and mean encoding, and how to perform feature crosses. ML models Linear regression (80 min) Logistic regression (35 min) Classification (70 min) Data Working with numerical data (85 min) Working with categorical data (50 min) Datasets, generalization, and overfitting (105 min) NL Concepts Foundational courses Advanced courses Guides Glossary Exercises Help Center Figure 1: Car heartiness (in-pounds) versus miles per gallon rating. As a car gets heavier, its miles per gallon rating generally decreases. We could create our own model by drawing a best fit line through the points. Model Miles per gallon (Label) 20 10 0.0 2.0 3.0 4.0 5.0 Pounds in 1000s (Feature) Figure 2: A best fit line drawn through the data from the previous figure. Linear regression equation In algebraic terms, the model would be defined as y' = b + w, x, where: y' is the predicted label—the output. b is the bias of the model. Bias is the same concept as the y-intercept in the algebraic equation for a line. In ML, bias is a parameter of the model and is calculated during training. - w, is the weight of the feature. Weight is the same concept as the slope in the algebraic equation for a line. Weight is a parameter of the model and is calculated during training. x, is a feature—the input. In ML, we write the equation for a linear regression model as: y' = b + w, x, Prediction Bias Weight Feature value Calculated from training