Manifold Grace

Canonical taxonomy updated: This is a historical research view. The current four-level classification separates AI categories, learning paradigms, methods, and model/system architectures; retired labels are traceable without being counted as distinct active types. Open current taxonomy (v1.2) · Matching CSV.

Research & Knowledge · AI and machine-learning development

Distinct AI types · Projects · Papers

One unique architecture family, model class or technical method per row. Every listed type has its own proposed project and research paper initiative. Related methods and broader learning paradigms are classified rather than counted repeatedly.

Current evidence-based register: 40 distinct base families or methods. This is not a claim that only 40 AI types exist. The previous set of 1,000 entries represented 40 families × 25 proposed scenarios, not 1,000 separate types. Expansion requires individually identified, nonduplicate types and credible source literature.

Taxonomy revision: AI application categories, model and system architectures, and statistical or machine-learning methods are now separated in three aligned tables. Survival analysis is classified as a statistical method, not an AI architecture. Open the three corrected taxonomy tables.

01 / Distinct AI families and methods

Each numbered row is unique. A project or paper link identifies a planned initiative, not a completed build or publication. Wikipedia is introductory context, not independent scientific validation.

40 unique types / methods
#AI type / methodClassificationCategoryWikipediaManifold Grace projectPaper initiativeStatus
1CNN feature hierarchymodel architectureComputer visionWikipediaProject AIT-0001Paper initiativeProposed
2Vision Transformermodel architectureComputer visionWikipediaProject AIT-0002Paper initiativeProposed
3Object detection networkmodel architecture classComputer visionWikipediaProject AIT-0003Paper initiativeProposed
4Semantic segmentation networkmodel architecture classComputer visionWikipediaProject AIT-0004Paper initiativeProposed
5Instance segmentation networkmodel architecture classComputer visionWikipediaProject AIT-0005Paper initiativeProposed
6Encoder Transformermodel architectureLanguage and knowledgeWikipediaProject AIT-0006Paper initiativeProposed
7Autoregressive Transformermodel architectureLanguage and knowledgeWikipediaProject AIT-0007Paper initiativeProposed
8Retrieval-augmented generationsystem integration patternLanguage and knowledgeWikipediaProject AIT-0008Paper initiativeProposed
9Sequence-to-sequence Transformermodel architectureLanguage and knowledgeWikipediaProject AIT-0009Paper initiativeProposed
10Knowledge-graph question answeringapplication architectureLanguage and knowledgeWikipediaProject AIT-0010Paper initiativeProposed
11Gradient-boosted treesmachine-learning algorithm familyPredictive and tabularWikipediaProject AIT-0011Paper initiativeProposed
12Generalised additive modelstatistical model familyPredictive and tabularWikipediaProject AIT-0012Paper initiativeProposed
13Temporal forecasting Transformermodel architecturePredictive and tabularWikipediaProject AIT-0013Paper initiativeProposed
14State-space sequence modelmodel architecturePredictive and tabularWikipediaProject AIT-0014Paper initiativeProposed
15Survival and hazard modelstatistical model familyPredictive and tabularWikipediaProject AIT-0015Paper initiativeProposed
16Graph convolutional networkmodel architectureGraphs and relational dataWikipediaProject AIT-0016Paper initiativeProposed
17Graph attention networkmodel architectureGraphs and relational dataWikipediaProject AIT-0017Paper initiativeProposed
18Relational graph neural networkmodel architectureGraphs and relational dataWikipediaProject AIT-0018Paper initiativeProposed
19Temporal graph neural networkmodel architectureGraphs and relational dataWikipediaProject AIT-0019Paper initiativeProposed
20Neural relational database modelresearch model/system conceptGraphs and relational dataWikipediaProject AIT-0020Paper initiativeProposed
21Denoising diffusion modelgenerative model architectureGenerative and multimodalWikipediaProject AIT-0021Paper initiativeProposed
22Latent diffusion modelgenerative model architectureGenerative and multimodalWikipediaProject AIT-0022Paper initiativeProposed
23Generative adversarial networkgenerative model architectureGenerative and multimodalWikipediaProject AIT-0023Paper initiativeProposed
24Variational autoencodergenerative model architectureGenerative and multimodalWikipediaProject AIT-0024Paper initiativeProposed
25Vision-language modelmultimodal model architecture classGenerative and multimodalWikipediaProject AIT-0025Paper initiativeProposed
26Tool-using LLM agentagent system architectureAgents and automationWikipediaProject AIT-0026Paper initiativeProposed
27Plan-and-execute agentagent orchestration patternAgents and automationWikipediaProject AIT-0027Paper initiativeProposed
28Multi-agent orchestrationmulti-agent system patternAgents and automationWikipediaProject AIT-0028Paper initiativeProposed
29AI-enabled BPM workflowbusiness workflow architectureAgents and automationWikipediaProject AIT-0029Paper initiativeProposed
30Event-driven decision agentagent system architectureAgents and automationWikipediaProject AIT-0030Paper initiativeProposed
31Vision-based robotic policyrobotics policy architectureRobotics and controlWikipediaProject AIT-0031Paper initiativeProposed
32Model-predictive controllercontrol methodRobotics and controlWikipediaProject AIT-0032Paper initiativeProposed
33Reinforcement learning policylearning-policy methodRobotics and controlWikipediaProject AIT-0033Paper initiativeProposed
34Imitation learning policylearning-policy methodRobotics and controlWikipediaProject AIT-0034Paper initiativeProposed
35Spiking neural controllerneural control architectureRobotics and controlWikipediaProject AIT-0035Paper initiativeProposed
36Rule-based expert systemsymbolic AI systemLogic, search and hybrid decisionWikipediaProject AIT-0036Paper initiativeProposed
37Constraint-satisfaction solverconstraint-solving algorithmLogic, search and hybrid decisionWikipediaProject AIT-0037Paper initiativeProposed
38Bayesian networkprobabilistic graphical modelLogic, search and hybrid decisionWikipediaProject AIT-0038Paper initiativeProposed
39Neuro-symbolic reasoning systemhybrid reasoning architectureLogic, search and hybrid decisionWikipediaProject AIT-0039Paper initiativeProposed
40Case-based reasoning systemreasoning methodLogic, search and hybrid decisionWikipediaProject AIT-0040Paper initiativeProposed

02 / Classification integrity

Computer vision and natural-language processing are application domains; supervised and unsupervised learning are training paradigms; neural networks and convolutional networks are related model families; robotic process automation is a workflow technology; and blockchain is an infrastructure technology. They belong in the wider AI projects taxonomy, but should not all be labelled model architectures. Learning paradigms reference.

The historical 1,000-row combinatorial research dataset is preserved separately with its existing identifiers. It must not be used to inflate the number of unique architectures.

02 / Common relational reasoning frameworks

A shared framework should provide interoperability where meaningful, not impose one representation or model on every task. It must not be conflated with the solution being evaluated. Candidates are listed by their likely scope and evidence limitations.

Native observationsArchitecture-specific extractionTyped relation contractContext and uncertainty analysisIndependent QA

FR-01 · Typed relation and context graph

Across most families: subject, relation, object, polarity, domain, context and conditions. A graph records claims but does not prove them.

FR-02 · Temporal event ledger

Especially forecasting, robotics and automation: event order, valid times, versions, state changes and corrections. Sequence does not imply causality.

FR-03 · Statistical and causal-hypothesis layer

Especially predictive analytics and intervention research: variables, populations, confounders, uncertainty and identifying assumptions. Causal claims require stronger evidence.

FR-04 · Constraints, permissions and obligations

Especially intelligent agents and workflow systems: permission checks, exceptions, actor roles, rule precedence and jurisdictional applicability.

FR-05 · Provenance, contradictions and revision

Across families: evidence identifiers, derivations, competing findings, responsible actors, model and dataset versions, recorded corrections.

Adoption criterion: A common framework must preserve domain-specific meaning and demonstrate useful improvements against independently specified tests. Over-generalisation is an evaluated failure, not a benefit.

03 / Specialised components for each architectural application

Each of the 40 base families has its own linked Wikipedia context, native relationship type and specialised component set. These are implementation candidates rather than verified deployments.

CategoryWikipedia-linked familyNative relationshipSpecialised components
Computer visionCNN feature hierarchylocal spatial receptive fieldsconvolution backbone; spatial feature pyramid; image calibration
Computer visionVision Transformerpatch-token global attentionpatch encoder; attention maps; positional geometry
Computer visionObject detection networkobject localisation and identitydetector head; box matching; non-max suppression
Computer visionSemantic segmentation networkdense pixel-level category assignmentmask decoder; pixel alignment; boundary checks
Computer visionInstance segmentation networkseparate masks for object instancesinstance tracking; mask matching; overlap verification
Language and knowledgeEncoder Transformercontextual bidirectional language representationtokeniser; encoder; entailment head
Language and knowledgeAutoregressive Transformernext-token generation with long-context dependenciesdecoder; context window management; factuality evaluator
Language and knowledgeRetrieval-augmented generationretrieval-to-answer grounding relationshipsretriever; reranker; citation entailment checker
Language and knowledgeSequence-to-sequence Transformerinput-output sequence transformationsencoder-decoder; alignment tracer; translation evaluator
Language and knowledgeKnowledge-graph question answeringentity-link and graph-path evidenceentity linker; SPARQL query builder; path verifier
Predictive and tabularGradient-boosted treesnonlinear feature-outcome interactionstabular preprocessing; tree ensemble; feature attribution
Predictive and tabularGeneralised additive modeladditive, interpretable predictorsspline feature functions; calibration plots; residual checks
Predictive and tabularTemporal forecasting Transformertime-varying series dependencieswindow sampler; horizon evaluator; temporal attention
Predictive and tabularState-space sequence modellatent evolving state relationshipsstate update kernel; filter; state diagnostics
Predictive and tabularSurvival and hazard modelevent-time and censoring relationshipscensoring handler; hazard estimation; calibration
Graphs and relational dataGraph convolutional networkneighbourhood topology aggregationgraph encoder; adjacency manager; graph split evaluator
Graphs and relational dataGraph attention networkattention-weighted neighbourhood relationshipsattention layers; edge sampler; neighbourhood audit
Graphs and relational dataRelational graph neural networktyped edges and heterogeneous relationsrelation-aware message passing; edge type validator
Graphs and relational dataTemporal graph neural networktime-stamped dynamic graph changesevent buffer; temporal neighbour sampler; leakage checks
Graphs and relational dataNeural relational database modelforeign-key and multi-table entity relationsschema parser; table join graph; relational encoder
Generative and multimodalDenoising diffusion modelnoise-to-sample denoising trajectoriesnoise scheduler; denoiser; output consistency checks
Generative and multimodalLatent diffusion modelcompressed latent-to-output relationshipslatent encoder; denoiser; decoder; reconstruction checks
Generative and multimodalGenerative adversarial networkgenerator-discriminator training dynamicsgenerator; discriminator; mode-collapse evaluator
Generative and multimodalVariational autoencoderlatent distribution and reconstruction relationsprobabilistic encoder; latent sampler; decoder
Generative and multimodalVision-language modelcross-modal image-text correspondencesvisual encoder; text encoder; alignment verifier
Agents and automationTool-using LLM agentmodel-to-tool requests and permissionstool registry; approval gate; audit trail
Agents and automationPlan-and-execute agentgoal decomposition and action dependenciesplanner; executor; plan validity checker
Agents and automationMulti-agent orchestrationdelegation and message provenanceagent router; role policy; inter-agent trace
Agents and automationAI-enabled BPM workflowtasks, transitions and business rulesBPMN engine; rule adapter; process conformance checker
Agents and automationEvent-driven decision agentevent conditions and triggered actionsevent bus; decision table; idempotency and rollback
Robotics and controlVision-based robotic policyvisual input to motor actioncamera perception; policy controller; safety envelope
Robotics and controlModel-predictive controllerfuture-state planning under constraintsdynamics model; trajectory optimiser; constraint monitor
Robotics and controlReinforcement learning policystate-action-reward dynamicspolicy/value networks; simulator; reward audit
Robotics and controlImitation learning policydemonstration-to-action generalisationtrajectory dataset; imitation learner; shift monitor
Robotics and controlSpiking neural controllerevent-driven neural timing dynamicsspiking units; temporal encoder; event simulator
Logic, search and hybrid decisionRule-based expert systemif-then inferences and exception rulesrule engine; conflict resolver; justification trace
Logic, search and hybrid decisionConstraint-satisfaction solvervariables, constraints and feasible assignmentsconstraint model; solver; proof-of-infeasibility reporter
Logic, search and hybrid decisionBayesian networkconditional probabilistic dependenceDAG model; inference engine; posterior calibration
Logic, search and hybrid decisionNeuro-symbolic reasoning systemlearned representations with explicit symbolic rulesneural encoder; logic layer; contradiction detector
Logic, search and hybrid decisionCase-based reasoning systemanalogy and difference across past casescase memory; similarity measure; adaptation validator

04 / Further columns for a research-grade register

The first table prioritises legibility. A second-stage expansion should add: input modality; training objective; supervision mode; parameterisation; inference mechanism; memory/state representation; output modality; deployment context; edge/cloud constraints; data provenance; intended use; limitations; model/dataset versions; evaluation dataset; result metrics; uncertainty; safety controls; legal applicability; system owner; evidence links; reviewer and reassessment trigger. Do not fill fields with guesses or treat missing research as completed.

Keep numerical performance and compliance claims separate from architecture categories. A research candidate without a prototype must have an explicit not tested status.

05 / Research basis and limitations

Wikipedia links provide reader context only; research validity and architecture naming require independent technical literature. Proposed hybrids are not automatically distinct established subfields, nor is business process automation itself necessarily a standalone neural-network architecture.