model

In general, any mathematical construct that processes input data and returns output. Phrased differently, a model is the set of parameters and structure needed for a system to make predictions. In supervised machine learning, a model takes an example as input and infers a prediction as output. Within supervised machine learning, models differ somewhat. For example: A neural network model consists of: - A set of hidden layers, each containing one or more neurons. - The weights and bias associated with each neuron. A decision tree model consists of: - The shape of the tree; that is, the pattern in which the conditions and leaves are connected. - The conditions and leaves. You can save, restore, or make copies of a model. Unsupervised machine learning also generates models, typically a function that can map an input example to the most appropriate cluster.

An algebraic function such as the following is a model:

The preceding function maps input values (x and y) to output. Similarly, a programming function like the following is also a model:

A caller passes arguments to the preceding Python function, and the Python function generates output (via the return statement). Although a deep neural network has a very different mathematical structure than an algebraic or programming function, a deep neural network still takes input (an example) and returns output (a prediction). A human programmer codes a programming function manually. In contrast, a machine learning model gradually learns the optimal parameters during automated training. ---