Glossary term
Glossary term
Architecture
A system (either hardware or software) that takes in one or more input values, runs a function on the weighted sum of the inputs, and computes a single output value. In machine learning, the function is typically nonlinear, such as ReLU, sigmoid, or tanh. For example, the following perceptron relies on the sigmoid function to process three input values:
In the following illustration, the perceptron takes three inputs, each of which is itself modified by a weight before entering the perceptron:
Perceptrons are the neurons in neural networks.
Created for this library
A research team uses the perceptron in its course material to introduce binary classification in plain mathematical terms.
An academic course on neural networks uses the perceptron as the simplest building block before moving to multi-layer networks.
A startup uses a perceptron as the simplest baseline against more complex models when explaining results to non-technical stakeholders.
Definition source: Google for Developers Machine Learning Glossary | Creative Commons Attribution 4.0 License