How deeply does Grokking Machine Learning cover compile()?

Defines loss, optimizer, and metric settings, then gives a classification example without detailing their internals.

Compile()

As explained in Grokking Machine Learning

A Keras model method that configures a model's loss function, optimizer, and evaluation metrics before training.

Before training a Keras model, compile() sets the loss function, optimizer, and metrics used during training. The loss measures model error, the optimizer guides training, and the metrics report how the model is doing. For categorical classification, one example uses categorical cross-entropy, Adam, and accuracy. section 10.3

model.compile(loss = 'categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

This call configures categorical cross-entropy loss, the Adam optimizer, and accuracy reporting. section 10.3

How Grokking Machine Learning covers it

liveBook manning.com

Read Grokking Machine Learning on liveBook Get the book at manning.com

Related concepts

performanceuses · Performance is the measurable effectiveness or operational behavior of a system under specified conditions, assessed through relevant qualities such as task results, speed, responsiveness, throughput, or resource use.
optimizationuses · Optimization is the systematic selection or adjustment of values, actions, or system designs to improve a specified objective, often subject to constraints.
objective functionuses · An objective function assigns values to candidate solutions, predictions, or parameter settings according to a criterion to be minimized or maximized.
compute_lossused by · compute_loss is a Keras model method that computes the configured loss together with applicable regularization losses.
Kerasuses · Keras is an open-source, high-level deep-learning API for building, training, evaluating, and deploying neural-network models.

This explainer was generated by Manning's knowledge graph from the text of Grokking Machine Learning. The section links point to the parts of the book it draws on.