Beginner · Fundamentals

Parameter

Visual diagram · (in preparation) · Math · (in preparation) · Worked example · 3 difficulty levels.

TL;DR. A configuration variable of the model that is learned from the training data.

Technical Definition

A configuration variable of the model that is learned from the training data.

How it works

In machine learning, parameters are internal variables of the model whose values are estimated or learned from the data during training. For example, in a neural network, the weights and biases are parameters. These parameters define the model's function and determine its output.

Related Concepts

• Model — A mathematical representation learned from data that maps inputs to outputs.
• Training — The process of adjusting a model's parameters so it learns patterns from labeled or unlabeled data.
• Hyperparameter — A configuration variable set before the training process begins, controlling aspects of the learning algorithm itself.