Linked from

The 25 pages that link to Neural network, each with the reason it gives.

• Artificial intelligenceBroader topic: Neural networks power many AI systems for perception, language, and prediction.

• ConnectionismBroader topic: Connectionist models implement cognitive processes with networks of this general form.

• DeepfakeRelated: Neural networks form the basis of most modern deepfake generation systems.

• Nonlinear systemRelated: Nonlinear activation functions let networks represent relationships beyond linear maps.

• Cognitive scienceBroader topic: Artificial and biological networks provide concrete models for distributed cognitive processing.

• Symbolic artificial intelligenceCompared with: Neural networks typically encode information in learned weights, unlike explicit symbolic structures.

• Gaussian processCompared with: Neural networks can scale to large datasets where exact Gaussian process inference becomes costly.

• Deep learningNarrower topic: Deep learning uses neural networks with multiple layers as its central computational structure.

• Expert systemCompared with: Its learned distributed representations differ from an expert system’s explicit rules.

• Convolutional neural networkNarrower topic: Convolutional networks are a specialized architecture within this broader model family.

• Eliminative materialismBroader topic: These models illustrate the non-classical architectures invoked in some arguments against propositional folk psychology.

• Large language modelNarrower topic: Large language models are neural networks trained to model language.

• BrainCompared with: It borrows a simplified neural metaphor but is not a biological brain.

• Computational neuroscienceNarrower topic: It is the broad modeling framework that many computational neuroscience models instantiate.

• Hebbian theoryNarrower topic: Hebbian changes to individual connections can reshape the behavior of the larger network.

• NeuroethologyCompared with: Comparisons with biological circuits expose what engineered models omit about bodies and natural behavior.

• Marvin MinskyRelated: Minsky studied neural networks early in his career, before emphasizing symbolic and distributed accounts of intelligence.

• Jerry FodorCompared with: Connectionist models challenge the symbolic architecture Fodor defended.

• Edge of chaosRelated: The hypothesis links near-critical dynamics to flexible signal processing in neural systems.

• History of artificial intelligenceRelated: Neural networks link early connectionist research with today’s deep-learning systems.

• Human brainCompared with: It borrows ideas from brains but differs in structure, learning, and embodiment.

• Computer GoRelated: Go programs use neural networks to estimate positions and guide move selection.

• Demis HassabisNarrower topic: DeepMind combines neural networks with learning and planning methods.

• Generative AINarrower topic: Neural networks are the main model family behind contemporary generative systems.

• Knowledge (artificial intelligence)Related: Its distributed parameters can encode useful patterns without a readable fact structure.