Computing systems where the computation is not based on a traditional mathematical model of computer

Computing systems where the computation is based on biological models (brains, intelligence, consciousness, genetic reproduction) or is using physical material of biological origin (biomolecules, DNA, biological neurons, etc.) to perform the computation. The computation can be digital, analogue or chemical in nature.

Classification in this group or its subgroups is expected only if the invention concerns the development of a computer. DNA and proteins biomaterials as such, should be classified in the relevant groups of (bio) chemistry.

Computers using actual physical material of biochemical origin or material as used in carbon-based living systems, i.e. biomolecules, proteins, cells or other biochemicals to perform computation.

Creation of synthetic life forms that are based on models of or are inspired by carbon-based life forms but are actually implemented on/or controlled by standard silicon-based computers.

Software simulations on standard silicon-based digital computers of systems exhibiting behaviour normally ascribed to life forms.

Physical computer controlled mechanical devices emulating/simulating existing biological life forms mainly implemented as physical robots in the form of animals (pets) or humans (humanoids or androids). These robots can be standalone or work in groups (e.g. Robocup team of robotic football players).

This group does not cover purely mechanical devices: there should always be some computer involved.

It should act, or at least have as function to look like an animal or a human.

Computation simulating or emulating the functioning of biological brains mainly implemented in non-biological material, i.e. electronics or optical material. It can be in digital electronic or analogue electronic or biological technology.

Applications of whatever sort just using neural networks with no description of the neural network itself are to be classified in the relevant application field only.

Documents specifying an architecture and a learning method should be classified in the respective subgroups of G06N 3/04 and G06N 3/08.

The specific architecture or layout of the neural network, how the neurons are interconnected. For the different architectures see the titles of the different subgroups.

Specific technologies for realizing these architectures are classified in G06N 3/06, learning methods in the subgroups of G06N 3/08 and for the physical realization in the subgroups of G06N 3/06.

Adaptive Resonance Theory (ART).

Adaptive Resonance Theory was a short live method of neural networks developed by Grossberg and Carpenter. This subgroup contains only documents on ART by Grossberg and Carpenter (obsolete technology).

Neural networks using some form of chaos or fractal technology or methods

Combinations of neural network technology and expert system technology.

Contains documents where expert systems and neural networks work together on the same level and also where expert systems are used to construct or control a neural network.

Combinations of neural network technology and fuzzy logic system technology.

Contains documents where fuzzy logic and neural networks work together on the same level, and also where fuzzy logic systems are used to construct or control a neural network.

Neural networks involving connections from the output of a neural network to the inputs of the same neural network.

Architecture of multiple neural networks can be connected in a parallel or in a series fashion. They can cooperate on the same level or one neural network can control other neural networks.

Parallel neural networks can also be used for fault tolerance when connecting to a voting system.

Several neural networks can also be trained in different ways or with different training examples and then combined in parallel in order to increase the reliability or accuracy.

Neocognitrons are an unique and specific architecture of neural network charaterized by its name.

The neocognitron is a hierarchical multilayered neural network and is a natural extension of cascading models.

In the neocognitron, multiple types of cells such as S-cells and C-cells are used to perform recognition task.

Contains only documents if the type of neural network is specifically called neocognitron.

Neural networks having as special feature that the neurons individually, or the weights connecting the neurons, or the architecture as a whole, have a probabilistic or statistical aspect.

All aspects of non-linear activation functions used in neurons, e.g. sigmoids, simple stepwise threshold functions, approximated sigmoid functions.

Only aspects of the non-linear activation function.

Neurons or neural networks having a temporal aspect e.g. spiking neurons or neural networks where the time-like dynamics are a specific aspect of the invention

This can be in digital but often in analogue technology.

These neurons are meant to be a more realistic simulation of real biological neurons

The technology used to physically construct the neurons or neural network : digital electronics, analog electronics, biochemical elements, optical elements

This head subgroups should contain no documents, all documents should fall in one of its lower subgroups

Using real biological neurons from a living being implemented on a substrate. These neurons can be externally activated and read-out. The interconnections can be fixed or the can be allowed to grow and evolve.

Neurons or interconnections implemented in dedicated digital electronics.

Neurons or interconnections implemented in dedicated analog electronics.

Neurons or interconnections implemented in dedicated optical components..

Neurons or neural networks using electro-optical, acousto-optical or opto-electronic components.

Means and methods of training or learning the neural networks. For specific training methods or algorithms see the different subgroups.

During the learning or training process of the neural network not only are the weights of the synapses changed but also is the architecture of the neural network changed. This can involve adding/deleting neurons or adding/deleting connections. between the neurons.

When during the training process it becomes clear that the size/capacity of the neural network is not sufficient, additional neurons or connections can be added to the network after which the training can resume. When it is found that certain neurons are not used or have no influence, they can be removed (pruning).

Training method whereby on the synapses of the neurons are adapted depending on the difference between the actual output of the neural network and the wanted output. This difference is used to adapt the weights of the synapses with an mathematical method that back-propagates form the higher layers to the lower layers of the neural network. Mainly used in multilayer neural networks. This implies a form of supervised learning.

The use of genetic algorithms for creating through a process of reproduction, mutation and fitness function an optimally functioning neural network using evoluationary techniques such as evolutionary programming, genetic algorithms, genetic programming, evolution startegies, etc.

Learning without direct supervision from unlabelled data. Neural networks are created and then it is observed how they function in the real world, as a result of the global functioning is the neural network further adapted. No sets of training input pairs are necessary.

Neural networks not implemented in specific special purpose electronics but simulated by a program on a standard general purpose digital computer

Specific software for specifying or creating neural networks to be simulated on a general purpose digital computer. Specific graphical user interfaces for this application.

Computation based on the principles of biological genetic processing (mutation, recombination, reproduction, selection of the fittest).

Using actual biological DNA molecules in test tubes. The problem is transcribed onto real DNA, biological reproduction, crossover, mutation is performed. The fitness is tested, the best scoring DNA molecules are selected and used for further iterative processing until the optimally performing DNA molecule is retrieved and the information on this DNA molecule is read out and transcribed back to a readable result.

Software simulations using the principles of mutation, crossover as exhibited in real biological genetic systems in the reproduction of biological cells or living beings e.g. humans.

This process involves the creation of a number of possible solutions, testing the different solutions (fitness), selecting the best performing ones, starting from these create a new set of possible solutions using reproduction and mutation, and reiterate through this process until an optimal or sufficiently performing solution is found.

Classification in this group is not expected when genetic algorithms are used in training neural networks. Applications of whatever sort just using genetic algorithms with no description of the genetic algorithm itself are to be classified in the relevant application field only.

Computer systems using knowledge bases or creating knowledge bases.

In particular, specific subjects are classified in the subgroups as it follows:

Systems using knowledge empirically, Heuristics. Systems based on empirical models are normally used when classic methods fail to find an exact solution in a short time.

Automatic theorem proving; constraint satisfaction; probability consistency check in a decision problem.

Knowledge based systems defined by the specific knowledge representation formalisms, knowledge engineering, knowledge acquisition and extraction, update of knowledge base, maintenance.

Knowledge systems using frames as knowledge representation including attributes and slots

Rule systems for specific applications are classified in the field of application, unless the invention is still about the rules formalism and/ or extraction and maintenance process itself.

Symbolic inference methods and devices. Programs with symbolic reasoning capabilities using knowledge. Inference systems.

Kind of logical inference that refers to the process of arriving at an explanatory hypothesis.

Abduction is about the most probable explanation for a fact given the sufficient premises

An inference mechanism that works backwards from the conclusion

Game-theory based applications are classified in their field of application when possible.

Expert system implemented in distributed programming units or multiple interacting intelligent autonomous components for example multi-agents systems.

Inference system that provides explanations of the inferences to the user in the context of diagnostic or decision support

Inference system that starts with the available data and makes inferences to derive more data. the inferences are performed forwards towards a goal by repetitive application of the modus ponens.

Transformation of exact inputs in fuzzy inputs with membership functions. The fuzzified inputs are processed in a fuzzy inference machine with fuzzy if-then rules. Depending on the degree of membership, several rules are fired in parallel. The consequents of each rule are aggregated into fuzzy outputs which are de-fuzzified or not de-fuzzified.

Computer systems based on mathematical models that cannot be classified in their application field.

When other types of Machine Learning are involved, also classify in G06N 20/00.

Inference system representing the probability dependencies between causes and effects in a directed acyclic graph model in which the inferences are modelled as the propagation of probabilities.

Classification in this group is not expected when probabilistic networks are used in neural networks (e.g. Boltzmann machines).

Applications of whatever sort just using Bayesian or Markov models with no description of the Bayesian or Markov model itself are to be classified in the relevant application field.

Learning of unknown parameters of the network to be classified also in G06N 20/00

Computer systems based on fuzzy logic

Classification in this group is not expected when fuzzy logics is used in combination with neural networks, nor when fuzzy logic is used in fuzzy inferencing.

Applications of whatever sort just using fuzzy logic with no description of the fuzzy logic itself are to be classified in the relevant application field.

Physical realizations of computer systems based on mathematical models

Fuzzy systems simulated on general purpose computers

Computer-based systems using chaos or non-linear models

Classification in this group is not expected when chaos models or non-linear models are used in neural networks.

Computation performed by a combination of atomic or subatomic particles where the interactions are no longer described by macroscopic physics but by the theory of quantum mechanics.

Models or logical architectures, as opposed to the hardware architectures covered by group G06N 10/40, of quantum computing, independent of whether or not a physical realisation is also disclosed. In particular, general logical/physical models of quantum computing, e.g. related to quantum circuit, are classified in group G06N 10/20.

The physical realisations of a specific model (see examples below) are classified in both G06N 10/20 and G06N 10/40.

A "quantum circuit" is a sequence of quantum logic gates, e.g. quantum gate array, quantum register or quantum random access memory. It should be noted that these are terms of art representing quantum models and should not be confused with physical circuit versions, e.g. electrical circuitry, in general. Quantum circuits are typically obtained via "quantum circuit synthesis", "quantum circuit decomposition" or "quantum compilers" (also not to be confused with "classical" compilers).

Typical examples of quantum gates: Clifford gates, controlled gates, e.g. cX, cY, cZ, CNOT, Hadamard gate, Pauli-X/Y/Z gates, SWAP gate, T gate, i.e. pi/8, Toffoli gate, i.e. CCNOT, Deutsch gate, Ising XX/YY/ZZ coupling gates, phase shift gates.

Other typical models of quantum computing: adiabatic quantum computation [AQC], topological quantum computing, quantum simulations, e.g. universal quantum simulator, quantum state machines, quantum cellular automata, quantum Turing machines [QTM].

Models wherein the units of quantum information are based on d-level quantum systems (qudits), e.g. using qutrits (d=3).

Physical realisations or hardware architectures, as opposed to the logical architectures covered by group G06N 10/20 for quantum computing, independent of whether or not a model of quantum computing is also disclosed. Executing models of quantum computing on a specific physical realisation (see examples below) are classified in both G06N 10/20 and G06N 10/40.

Physical realisations typically fall in one of the following categories: superconducting quantum computers, e.g. based on charge qubits, flux qubits, phase qubits, Transmon, Xmon, trapped ion/atom quantum computers, e.g. based on Paul ion trap, optical lattices, spin-based quantum computers, e.g. based on quantum dots, NMR, NMRQC, nitrogen-vacancy centres, fullerenes, Kane or Loss-DiVincenzo quantum computers, based on quantum optics, e.g. linear optical quantum computers.

Examples of quantum components and qubit manipulations: qubit coupling, control or readout, storing quantum states, quantum processor, quantum bus, quantum memory, quantum network (for computations), quantum repeater (for computations).

All quantum algorithms and not limited to, e.g. quantum optimisation (see examples below). In particular, quantum computing algorithms for specific problems, e.g. NP problem, are classified in group G06N 10/60. Algorithms based on quantum optimisation also includes so-called "hybrid quantum-classical algorithms". The physical realisations of a specific algorithm (see example below) are classified in both G06N 10/40 and G06N 10/60.

Quantum algorithms typically fall in one of the following categories:

Arrangements to achieve fault-tolerant quantum computations. Typical solutions rely on the introduction of ancillary, i.e. additional or auxiliary qubits, such as stabiliser codes, but this place also covers ancilla-free solutions, i.e. no additional qubit necessary. Other examples: bit flip codes, sign flip codes, Shor code, topological codes, e.g. surface codes, planar codes, toric codes.

Arrangements for assessing the quality of quantum computers, whether characterised by a metrics or figure of merits, e.g. quantum fidelity, quantum volume, quantum purity, error rate, or by its calculation or measurement, e.g. randomized benchmarking [RB], cross-entropy benchmarking [CEB], random circuit sampling [RCS].

All arrangements for quantum programming, such as quantum instruction sets, quantum software development kits, or quantum programming languages. Typical examples: Quil, Qiskit, or QCL.

Platforms for simulating or accessing the quantum computers, such as cloud-based quantum computing. Typical examples: IBM Q Experience, Quantum Inspire, Azure Quantum, Amazon Braket, Rigetti Quantum Cloud Services, Quantum Playground.

Methods or apparatus giving a machine (in its broadest sense) the ability of adapting or evolving according to experience gained by the machine. A machine in its broadest sense is understood as either an "abstract machine" or a physical one (i.e. a computer).

Machine learning processes where multiple learners (i.e. learning algorithms) are trained to solve the same problem, to obtain better predictive performance than could be obtained from any of the constituent learning algorithms alone.

This group is residual to the whole of the subclass, i.e. it covers subject matter which falls under the scope of G06N and which is not covered by its groups.

Therefore this main group should be rarely used or not used for classification.

Whenever a new computing technology is identified, which is not covered by the other main groups of G06N, it is recommended to create a new subgroup here for that new subject.

Systems where the computational elements are implemented on the molecular level using inorganic molecules e.g. molecular switches.

Classification in this group is not expected when computational elements implement quantum computers.