Artificial neural network
An artificial neural network (ANN), also called a neural network or connectionist network, is a computational mathematical model developed in inspiration from brain or cognitive processes that occur in a natural neural network and used in machine learning. This type of network usually contains many information units (inputs and outputs) connected to one another, with connections that often pass through “hidden” information units (hidden layers).
On this page
Source content checked . English translation published 2026-10-27.
In business automation
An artificial neural network is the mechanism behind models used for classification, field extraction, and agents. In business automation, you do not build the network from scratch; you select a ready-made model and evaluate its output using your organization’s data.
Examples
These examples illustrate a possible workflow. Adapt the connections and rules to your own systems.
Classifying supplier documents
The finance department sends invoices to a model based on a neural network to identify the document type. An invoice that does not meet the confidence threshold is sent to a human reviewer instead of being automatically recorded as an approved expense.
Relevant tools
- ChatGPT
- The service uses network-based models; evaluate the output on your organization’s documents instead of copying a generic example.
What to check
- Accuracy demonstrated on general images does not guarantee correct recognition of your forms.