Neural Network
A neural network is a computational model loosely inspired by biological neurons, in which weighted connections between simple units learn to map inputs to outputs.
What is Neural Network?
A neural network is built from layers of nodes. Each connection has a weight that is updated during training using gradient descent and back-propagation. Architectures include feed-forward networks, convolutional networks for images, recurrent networks for sequences, and transformer networks for language. The term is broad and now usually refers to deep architectures with many layers.
How does Neural Network apply to enterprise AI?
Most enterprise AI components shipped in 2026 are neural networks under the hood, even when wrapped in a higher-level API. Buyers do not configure them directly, but model choice, size, and provider have direct cost, latency, and compliance implications.
Related terms
- Deep Learning - Deep Learning is a branch of machine learning that uses multi-layer neural networks to learn hierarchical representations from raw data.
- Foundation Model - A foundation model is a large neural network pre-trained on broad data and designed to be adapted to many downstream tasks.
- Inference - Inference is the act of running a trained model on new inputs to produce predictions or generated output.
- Embedding - An embedding is a dense numerical vector that represents a piece of content (text, image, audio) in a way that semantically similar items end up close together in the vector space.
External references
Need help applying Neural Network to your enterprise? Submit a short brief and we reply within one business day.