Neural Network
Quick Answer
A neural network is a computational model loosely inspired by the human brain, consisting of interconnected layers of nodes (neurons) that transform inputs into outputs through weighted mathematical operations learned during training.
In Depth
What Neural Network really means
Each neuron in the network takes one or more inputs, applies a weight and a non-linear activation function, and passes the result to the next layer. During training, the network adjusts its weights via backpropagation to minimise a loss function that measures prediction error.
Neural networks come in many architectures, including feed-forward networks for tabular data, convolutional networks for images, recurrent networks for sequences and transformers for language. Architecture choice matters more than raw size for most business problems.
Why It Matters
Business relevance for UK organisations
Neural networks are the workhorse behind most modern AI features, from email autocomplete to product recommendations. For UK SMEs, the practical decision is usually whether to fine-tune a pre-trained network or to call a managed API.
Real-world example
How this shows up in practice
A Birmingham logistics firm trained a lightweight neural network on its historical delivery data to predict route ETAs within a 4-minute margin of error.
Related Terms
Continue exploring
Deep Learning
Deep Learning is a branch of machine learning that uses multi-layered neural networks to learn highly complex patterns directly from raw data such as images, audio and text, without the need for hand-crafted feature engineering.
TechnicalTransformer
The transformer is a neural network architecture introduced in 2017 that uses a mechanism called self-attention to process sequences in parallel. It is the foundational architecture behind nearly all modern large language models and many leading vision and audio models.
BasicsTraining Data
Training data is the dataset used to teach a machine learning model the patterns it needs to perform its task. The quality, quantity, diversity and recency of training data directly determine how accurate and fair the resulting model will be.
BasicsInference
Inference is the phase in which a trained model is used to produce predictions or outputs on new data. While training happens once (or periodically), inference happens every time a user interacts with an AI system, making it the dominant cost in most production deployments.