TensorFlow Fundamentals

TensorFlow is an end-to-end machine learning platform. It gives you numerical computation, automatic differentiation, model-building APIs, training support, and export paths in one ecosystem. You use it when a model must move from an experiment into a repeatable application or a target runtime.

Start with the workflow, not the package names. You prepare examples, define a model, choose how training measures error, adjust trainable weights, and evaluate the result on data held back from training. A model can fit its training data and still fail on new data. Evaluation is the check that matters.

The core mental model