Glossary

Neural network

A model made of layers of connected nodes that learns to map inputs to outputs by adjusting connection weights during training.

Also called: artificial neural network, ANN

A neural network is a model made of layers of simple computational units, called neurons or nodes, connected by weighted links loosely inspired by biological neurons. An input layer receives the features, one or more hidden layers transform them through weighted sums and a nonlinear activation function, and an output layer produces the prediction: a class probability for classification or a number for regression.

The network learns by adjusting its connection weights to reduce prediction error on training data, using an algorithm called backpropagation combined with gradient descent, repeated over many passes through the data. A network with more layers and parameters can represent more complex relationships, which is the basis of deep learning, but also has more capacity to memorize noise, so it needs enough data and regularization to avoid overfitting.

Neural networks are the standard approach for unstructured data, images, audio, text, where relationships are too complex for simpler models to capture well, and they underlie most modern computer vision and language systems. Compared with a decision tree or random forest on tabular data, they usually need far more data and hyperparameter tuning to perform competitively, and their internal reasoning is harder to explain.

Last reviewed September 22, 2026

In the index now

Related terms

Deep learning Machine learning using neural networks with many layers, able to learn complex patterns directly from raw data such as images or text. Training data The dataset with known outcomes that a machine learning model learns patterns from before being used to predict new cases. Overfitting When a model learns the noise and specific quirks of its training data so closely that it performs poorly on new data. Classification A supervised learning task that assigns each input to one of a fixed set of discrete categories or labels. Hyperparameter tuning The process of finding the settings that control how a model learns, such as learning rate or tree depth, rather than what it learns.

Related tools

Amazon Neptune Fully managed AWS graph database supporting both property-graph (Gremlin, openCypher) and RDF (SPARQL) query models. PyTorch Forecasting Open-source deep-learning forecasting library built on PyTorch and PyTorch Lightning for panel/multi-series data.

Related guides

Image and video analytics, explained How pictures and video become structured data — computer vision, the labeled training data it depends on, and how streaming teams measure watch quality.