Hyperparameters
Hyperparameters are configuration variables set by the user *before* the training process of a machine learning model begins, rather than being learned from the data. Examples include the learning rate (how quickly the model adjusts its weights), the number of layers in a neural network, or the strength of regularization. Their values significantly impact the model's performance.
They are like the oven temperature and cooking time you choose before baking a cake, impacting the final outcome but not mixed into the batter itself.
Careful selection and tuning of hyperparameters are essential for optimizing model performance and preventing issues like overfitting or underfitting.
Learn one new AI thing every day.
Daily Deck sends you seven plain-English cards like this every morning. Free.
Start free