Daniel & Friends / Glossary / Neural network
AI and automationNeural network
A neural network is a mathematical model made of layers of connected nodes, loosely inspired by the brain. During training, the weights of the connections are adjusted until the network produces correct outputs. Language models are very large neural networks with an architecture called a transformer.
Daniel Votruba ·
In practice
As a user you do not see inside one and usually do not need to. Remember that its decisions are hard to explain, which matters for sensitive decisions.
Related terms
- Deep learning: Deep learning is a branch of machine learning that uses neural networks with many layers.
- Machine learning (ML): Machine learning is the area of AI in which a computer learns patterns from data and uses them to predict or decide, instead of following rules a programmer wrote out.
- Large language model (LLM): A large language model is a model trained on a huge amount of text that predicts the next words and can write, summarise and answer.
- Foundation model: A foundation model is a large model pre-trained on a huge amount of data that serves as the base for many different tasks.
More terms in the group AI and automation
NLP (natural language processing) · Multimodal model · No-code and low-code · Multi-agent system · Open-weight model · Model evaluation (evals) · Predictive analytics · Model bias (AI bias) · Prompt · MCP (Model Context Protocol) · Prompt engineering · Prompt injection · RAG (retrieval-augmented generation) · Jailbreak (AI) · Reasoning model · Inference and latency · RPA (robotic process automation) · Human in the loop · Semantic search · Hallucination · Shadow AI · Guardrails · Small language model (SLM) · Grounding
Terms in practice
Need help putting them to work?
Terms are one thing, putting them to work is another. We go through which of them pay off for you and say so plainly. You get a first opinion for free and we reply within 24 hours.
Book a call