Artificial neural network
In machine learning, a neural network (NN) or artificial neural network (ANN) is a computational model inspired by the structure and functions of biological neural networks.
At a glance
Key signals
25% cross fields · reaches 6 more
- Computer Science
- Machine Learning
- Explanation
- Examples
- Misconception
- Sourced relations 4
- Attribution
Dependencies
What this concept builds on and what it makes possible — derived from the atlas’s dependency, causal and structural relations, not from every related edge.
Enables · leads to
Deep learningdepends onArtificial neural networkEstablished
deep learning depends on artificial neural network.
Mechanism: Deep learning depends on neural networks with many layers: stacking layers lets a model learn features of rising abstraction from raw data.
- Wikipedia (English & German editions) verifiedmoderate evidence
System context
Artificial neural networkis part ofArtificial intelligenceEstablished
Open Artificial intelligence →
artificial neural network is part of artificial intelligence.
Mechanism: A neural network is an AI model loosely inspired by the brain: layers of simple units adjust their connections to recognise patterns.
- Wikidata verifiedmoderate evidence
Artificial neural networkis part ofMachine learningEstablished
artificial neural network is part of Machine learning.
Mechanism: Neural networks are a family of machine-learning models: they learn by tuning the weights on their connections to reduce error.
- Wikidata verifiedmoderate evidence
Transformer (attention)is aArtificial neural networkEstablished
Open Transformer (attention) →
The architecture behind LLMs.
Mechanism: The transformer is a neural network whose self-attention weighs every token against every other.
Structural role & consequence
Interpreted from the current atlas graph — what the connections mean, not just how many there are.
Removing this node lengthens the structural route between Neural signal and Neuroinformatics from 2 to 3 steps (they stay connected — alternative routes exist).
structural · Structural removal simulation — not a historical or causal counterfactual.
25% of its relationships cross field boundaries, reaching 6 other disciplines — unusual in a discipline where most concepts stay within their field.
structural · Structural graph analysis — not a claim of importance, causation or history.
Currently dark in the atlas: no key date stored · 8 of 8 of its relations lack claim-level evidence.
atlas representation · Describes the current Thinking OS representation, not the state of the world.
Structural neighbourhood: 8 → 36 → 186 concepts reachable within 3 hops.
structural · Structural reach — being reachable is not the same as being understood.
cross-field
6 within-field, 2 cross-field
Strengths & constraints
Constraints
- Evidence coverage currently thin in the atlas — few of its relationships carry claim-level evidence. atlas representation
- No dated history stored — the atlas records no key date for this concept. atlas representation
Conditions
- Read structurally — most of its relationships carry no external evidence yet, so claims here are graph-derived. structural
Dependency radial
What this concept builds on (left) and what it makes possible (right) — derived from dependency and causal relations.
What builds on this
1 concept build on this directly, 2 in total, across 3 disciplines.
Structural downstream reach along dependency edges — not a claim of historical necessity.
Seen through each discipline
How this concept sits in each of its fields — derived from its real connections in the graph, not asserted.
Through this lens it connects to Machine learning, Artificial intelligence, Deep learning and Backpropagation.
Artificial neural network through the Computer Science lens →
Through this lens it connects to Machine learning and Deep learning.
Artificial neural network through the Machine Learning lens →
Check yourself
A quick check against a common misconception. Nothing is scored — picking the tempting-but-wrong answer just flags an idea worth revisiting.
Which statement is correct?
An artificial neural network works just like a human brain.
It borrows a loose metaphor from neurons but is vastly simpler and works differently — it tunes numerical weights by optimisation, with no biology, chemistry or understanding.
Look for: Learner assumes neural networks think or understand like brains.
Related ideas to explore
Concepts that look related but are not yet connected here — candidates for a connection to reason about, not established links.
This idea also appears in…
The same structure shows up in other disciplines. These are real recurrences drawn from the graph — a starting point for asking “what carries over, and what changes?”
Networks50 disciplines · 35 concepts
Concepts
shares a mental model
shares a mental model
shares a mental model
shares a mental model
shares a mental model
shares a mental model
An artificial neural network is a computer system loosely inspired by the brain. It is made of simple units that pass numbers to each other; by adjusting the strength of those connections, the network learns to recognise patterns from examples.
An artificial neural network is layers of nodes connected by weighted links. Each node sums its inputs, applies a simple function and passes the result on; training adjusts the weights so the whole network maps inputs to desired outputs — the engine behind modern deep learning.
Mental models at work here
- Connects 8 other ideas across 2 disciplines.
- A cross-disciplinary bridge — its connections reach into 6 other fields.
- Most of its connections are of the “Kind & structure” kind.
- It exercises 1 reusable thinking pattern.
Derived from the graph’s real structure — observations, not a score.
Sources
- Wikipedia (English & German editions) verifiedmoderate evidence
- Wikidata verifiedmoderate evidence
- From Artificial Neural Network to Realistic Neural Network verified
- Toroidal neural network processor: Multiple learning algorithm support verified
- Machine Learning and Artificial Neural Network (2018) verified
- Journal of Artificial Intelligence, Machine Learning and Neural Network verified