Hyperparameters
Hyperparameters are configuration settings that are external to the AI model itself and are set by the developer before the training process begins. These settings, unlike model parameters which are learned during training, control key aspects of the learning algorithm, such as the learning rate or the number of layers in a neural network. Their values significantly impact how well a model learns and generalizes to new data.
Hyperparameters are like the pre-set controls on a sewing machine, like needle speed or stitch length, that you adjust before you start sewing.
Properly tuning hyperparameters is crucial for achieving optimal model performance and preventing issues like underfitting or overfitting.
Learn one new AI thing every day.
Daily Deck sends you seven plain-English cards like this every morning. Free.
Start free