G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELSIn this subclass non-limiting references (in the sense of paragraph 39 of the Guide to the IPC) may still be displayed in the scheme. G06N3/00 G06N3/00Computing arrangements based on biological models G06N3/002Biomolecular computers, i.e. using biomolecules, proteins, cells using DNA G06N3/123; using neurons G06N3/061 G06N3/004Artificial life, i.e. computing arrangements simulating life G06N3/006based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] G06N3/008based on physical entities controlled by simulated intelligence so as to replicate intelligent life forms, e.g. based on robots replicating pets or humans in their appearance or behaviour G06N3/02Neural networks G06N3/04Architecture, e.g. interconnection topologyGroup G06N3/04 is impacted by reclassification into groups G06N3/0464, G06N3/0475, G06N3/0495 and G06N3/0499.
All groups listed in this Warning should be considered in order to perform a complete search. G06N3/0409Adaptive resonance theory [ART] networks G06N3/0418using chaos or fractal principles G06N3/042Knowledge-based neural networksLogical representations of neural networks G06N3/043based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS] G06N3/044Recurrent networks, e.g. Hopfield networksGroup G06N3/044 is impacted by reclassification into group G06N3/0442.
Groups G06N3/044 and G06N3/0442 should be considered in order to perform a complete search. G06N3/0442characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]Group G06N3/0442 is incomplete pending reclassification of documents from group G06N3/044.
Groups G06N3/044 and G06N3/0442 should be considered in order to perform a complete search. G06N3/045Combinations of networksGroup G06N3/045 is impacted by reclassification into group G06N3/0455.
Groups G06N3/045 and G06N3/0455 should be considered in order to perform a complete search. G06N3/0455Auto-encoder networksEncoder-decoder networksGroup G06N3/0455 is incomplete pending reclassification of documents from group G06N3/045.
Groups G06N3/045 and G06N3/0455 should be considered in order to perform a complete search. G06N3/0463Neocognitrons G06N3/0464Convolutional networks [CNN, ConvNet]Group G06N3/0464 is incomplete pending reclassification of documents from group G06N3/04.
Groups G06N3/04 and G06N3/0464 should be considered in order to perform a complete search. G06N3/047Probabilistic or stochastic networksGroup G06N3/047 is impacted by reclassification into group G06N3/0475.
Groups G06N3/047 and G06N3/0475 should be considered in order to perform a complete search. G06N3/0475Generative networksGroup G06N3/0475 is incomplete pending reclassification of documents from groups G06N3/04 and G06N3/047.
Groups G06N3/04, G06N3/047, and G06N3/0475 should be considered in order to perform a complete search. G06N3/048Activation functions G06N3/049Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs G06N3/0495Quantised networksSparse networksCompressed networksGroup G06N3/0495 is incomplete pending reclassification of documents from group G06N3/04.
Groups G06N3/04 and G06N3/0495 should be considered in order to perform a complete search. G06N3/0499Feedforward networksGroup G06N3/0499 is incomplete pending reclassification of documents from group G06N3/04.
Groups G06N3/04 and G06N3/0499 should be considered in order to perform a complete search. G06N3/06Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons G06N3/061using biological neurons, e.g. biological neurons connected to an integrated circuit G06N3/063using electronic means G06N3/065Analogue means G06N3/067using optical means G06N3/0675using electro-optical, acousto-optical or opto-electronic means G06N3/08Learning methodsGroup G06N3/08 is impacted by reclassification into groups G06N3/0895, G06N3/09, G06N3/091, G06N3/092, G06N3/094, G06N3/096, G06N3/098 and G06N3/0985.
All groups listed in this Warning should be considered in order to perform a complete search. G06N3/082modifying the architecture, e.g. adding, deleting or silencing nodes or connections G06N3/084Backpropagation, e.g. using gradient descent G06N3/086using evolutionary algorithms, e.g. genetic algorithms or genetic programming G06N3/088Non-supervised learning, e.g. competitive learning G06N3/0895Weakly supervised learning, e.g. semi-supervised or self-supervised learningGroup G06N3/0895 is incomplete pending reclassification of documents from group G06N3/08.
Groups G06N3/08 and G06N3/0895 should be considered in order to perform a complete search. G06N3/09Supervised learningGroup G06N3/09 is incomplete pending reclassification of documents from group G06N3/08.
Groups G06N3/08 and G06N3/09 should be considered in order to perform a complete search. G06N3/091Active learningGroup G06N3/091 is incomplete pending reclassification of documents from group G06N3/08.
Groups G06N3/08 and G06N3/091 should be considered in order to perform a complete search. G06N3/092Reinforcement learningGroup G06N3/092 is incomplete pending reclassification of documents from group G06N3/08.
Groups G06N3/08 and G06N3/092 should be considered in order to perform a complete search. G06N3/094Adversarial learningGroup G06N3/094 is incomplete pending reclassification of documents from group G06N3/08.
Groups G06N3/08 and G06N3/094 should be considered in order to perform a complete search. G06N3/096Transfer learningGroup G06N3/096 is incomplete pending reclassification of documents from group G06N3/08.
Groups G06N3/08 and G06N3/096 should be considered in order to perform a complete search. G06N3/098Distributed learning, e.g. federated learningGroup G06N3/098 is incomplete pending reclassification of documents from group G06N3/08.
Groups G06N3/08 and G06N3/098 should be considered in order to perform a complete search. G06N3/0985Hyperparameter optimisationMeta-learningLearning-to-learnGroup G06N3/0985 is incomplete pending reclassification of documents from group G06N3/08.
Groups G06N3/08 and G06N3/0985 should be considered in order to perform a complete search. G06N3/10Interfaces, programming languages or software development kits, e.g. for simulating neural networks G06N3/105Shells for specifying net layout G06N3/12using genetic models G06N3/123DNA computing G06N3/126Evolutionary algorithms, e.g. genetic algorithms or genetic programming G06N5/00Computing arrangements using knowledge-based models G06N5/01Dynamic search techniquesHeuristicsDynamic treesBranch-and-bound G06N5/013Automatic theorem proving G06N5/02Knowledge representationSymbolic representation G06N5/022Knowledge engineeringKnowledge acquisition G06N5/025Extracting rules from data G06N5/027Frames G06N5/04Inference or reasoning models G06N5/041Abduction G06N5/042Backward inferencing G06N5/043Distributed expert systemsBlackboards G06N5/045Explanation of inferenceExplainable artificial intelligence [XAI]Interpretable artificial intelligence G06N5/046Forward inferencingProduction systems G06N5/047Pattern matching networksRete networks G06N5/048Fuzzy inferencing G06N7/00Computing arrangements based on specific mathematical models G06N7/01Probabilistic graphical models, e.g. probabilistic networks G06N7/02using fuzzy logic computing arrangements based on biological models G06N3/00; computing arrangements using knowledge-based models G06N5/00 G06N7/023Learning or tuning the parameters of a fuzzy system G06N7/026Development tools for entering the parameters of a fuzzy system G06N7/04Physical realisation G06N7/043Analogue or partially analogue implementation G06N7/046Implementation by means of a neural network neural networks using fuzzy logic G06N3/043 G06N7/06Simulation on general purpose computers G06N7/08using chaos models or non-linear system models G06N10/00Quantum computing, i.e. information processing based on quantum-mechanical phenomenaGroup G06N10/00 is impacted by reclassification into groups G06N10/20, G06N10/40, G06N10/60, G06N10/70 and G06N10/80.
All groups listed in this Warning should be considered in order to perform a complete search. G06N10/20Models of quantum computing, e.g. quantum circuits or universal quantum computersGroup G06N10/20 is incomplete pending reclassification of documents from group G06N10/00.
Groups G06N10/00 and G06N10/20 should be considered in order to perform a complete search. G06N10/40Physical realisations or architectures of quantum processors or components for manipulating qubits, e.g. qubit coupling or qubit controlGroup G06N10/40 is incomplete pending reclassification of documents from group G06N10/00.
Groups G06N10/00 and G06N10/40 should be considered in order to perform a complete search. G06N10/60Quantum algorithms, e.g. based on quantum optimisation, quantum Fourier or Hadamard transformsGroup G06N10/60 is incomplete pending reclassification of documents from group G06N10/00.
Groups G06N10/00 and G06N10/60 should be considered in order to perform a complete search. G06N10/70Quantum error correction, detection or prevention, e.g. surface codes or magic state distillationGroup G06N10/70 is incomplete pending reclassification of documents from group G06N10/00.
Groups G06N10/00 and G06N10/70 should be considered in order to perform a complete search. G06N10/80Quantum programming, e.g. interfaces, languages or software-development kits for creating or handling programs capable of running on quantum computersPlatforms for simulating or accessing quantum computers, e.g. cloud-based quantum computingGroup G06N10/80 is incomplete pending reclassification of documents from group G06N10/00.
Groups G06N10/00 and G06N10/80 should be considered in order to perform a complete search. G06N20/00Machine learning G06N20/10using kernel methods, e.g. support vector machines [SVM] G06N20/20Ensemble learning G06N99/00Subject matter not provided for in other groups of this subclass G06N99/007Molecular computers, i.e. using inorganic molecules using biomolecules G06N3/002