Abstract: A method of performing an inference task on a knowledge graph comprising semantic triples of entities, wherein entity types are subject, object and predicate, and wherein each semantic triple comprises one of each entity type, using a quantum computing device, wherein a first entity of a first type and a second entity of a second type are given and the inference task is to infer a third entity of the third type. By performing specific steps and choosing values according to specific prescriptions, an efficient and resource-saving method is developed that utilizes the power of quantum computing systems for inference tasks on large knowledge graphs. An advantageous value for a cutoff threshold for a cutoff based on singular values of a singular value tensor decomposition is prescribed, and a sequence of steps is developed in which only the squares of the singular values are of consequence and their signs are not.

Abstract: A method for computing joint torques applied by actuators to perform a control of a movement of a robot arm having several degrees of freedom is provided. The method includes the act of providing, by a trajectory generator, trajectory vectors specifying a desired trajectory of the robot arm for each degree of freedom. The trajectory vectors are mapped to corresponding latent representation vectors that capture inherent properties of the robot arm using basis functions with trained parameters. The latent representation vectors are multiplied with trained core tensors to compute the joint torques for each degree of freedom.

Abstract: Various examples generally relate to knowledge graphs including entities and links associated with semantic triples including subject-predicate-object. Various examples specifically relate to quantum-machine learning of knowledge graphs. Further examples relate to a quantum-machine-assisted inference on knowledge graphs.

Abstract: The invention relates to a computer-implemented method for providing a trained function (36) to determine a treatment.

Abstract: A method for operating a network, such as an automation network, for example, has multiple node devices provided that are networked to one another. There is a global time available, and the node devices record their operating parameters. The operating parameters are allocated to a respective address element as content elements in order to be stored in a tensorial database structure. Control or adaptation of the operation of the network with its node devices and couplings is facilitated thereby. The method is suitable particularly for use in supply networks, automated production installations, communication networks, transport networks and logistical networks. The proposed storing allows easy visualisation, depiction and evaluation of operating states of the network and of its node devices.

Abstract: The present invention provides an improved method for providing an artificial neural network for data imputation using a generative adversarial network framework. Binary values in categorizing data fields of original data sets are replaced with smoothed-out values that include a degree of randomization but from which the original information can be retrieved. In this way, unintended hints to the discriminating network are minimized and thus the performance of the generative network is improved.

Abstract: A method of performing an inference task on a knowledge graph comprising semantic triples of entities, wherein entity types are subject, object and predicate, and wherein each semantic triple comprises one of each entity type, using a quantum computing device, wherein a first entity of a first type and a second entity of a second type are given and the inference task is to infer a third entity of the third type. By performing specific steps and choosing values according to specific prescriptions, an efficient and resource-saving method is developed that utilizes the power of quantum computing systems for inference tasks on large knowledge graphs. An advantageous value for a cutoff threshold for a cutoff based on singular values of a singular value tensor decomposition is prescribed, and a sequence of steps is developed in which only the squares of the singular values are of consequence and their signs are not.

Abstract: The present invention is related to a computer-implemented method of training artificial intelligence (AI) systems or rather agents (Maximum Entropy Regularised multi-goal Reinforcement Learning), in particular, an AI system/agent for controlling a technical system. By constructing a prioritised sampling distribution q(ôg) with a higher entropy q(Ôg) than the distribution p(ôg) of goal state trajectories ôg and sampling the goal state trajectories ôg with the prioritised sampling distribution q(ôg) the AI system/agent is trained to achieve unseen goals by learning from diverse achieved goal states uniformly.

Abstract: A method for computing joint torques applied by actuators to perform a control of a movement of a robot arm having several degrees of freedom is provided. The method includes the act of providing, by a trajectory generator, trajectory vectors specifying a desired trajectory of the robot arm for each degree of freedom. The trajectory vectors are mapped to corresponding latent representation vectors that capture inherent properties of the robot arm using basis functions with trained parameters. The latent representation vectors are multiplied with trained core tensors to compute the joint torques for each degree of freedom.

Abstract: Various examples generally relate to knowledge graphs including entities and links associated with semantic triples including subject-predicate-object. Various examples specifically relate to quantum-machine learning of knowledge graphs. Further examples relate to a quantum-machine-assisted inference on knowledge graphs.

Abstract: A method and system of determining influence of attributes in Recurrent Neural Networks (RNN) trained on therapy prediction is provided. For each output neuron zkl a relevance score Rkl is decomposed into decomposed relevance scores Rk?jl for each component xjl of an input vector x1 and all decomposed relevance scores Rk?jl of the present step l are combined to a relevance score Rjl for the next step l?1.

Abstract: A method and apparatus for automatic recognition of similarities between perturbations in a network, the apparatus includes a memory unit for storing a first data array of multiple perturbation data snapshots each recorded in response to a perturbation observed in the network; a generation unit adapted to generate by machine learning a data model of perturbations trained on the first data array, wherein the trained data model provides a latent vector representation for each of the perturbations; a recording unit adapted to record a perturbation data snapshot if a perturbation is observed during operation of said network and adapted to provide a corresponding second data array for the recorded perturbation data snapshot; and a processing unit adapted to derive a latent vector representation for the observed perturbation from the second data array using the trained data model of perturbations.

Abstract: A method is provided for calculating a relation indicator for a relation between entities based on an optimization procedure. The method combines the strong relational learning ability and the good scalability of the RESCAL model with the linear regression model, which may deal with observed patterns to model known relations. The method may be used to determine relations between objects, for instance entries in a database, such as a shopping platform, medical treatments, production processes, or in the context of the Internet of Things, in a fast and precise manner.

Abstract: A method for operating a network, such as an automation network, for example, has multiple node devices provided that are networked to one another. There is a global time available, and the node devices record their operating parameters. The operating parameters are allocated to a respective address element as content elements in order to be stored in a tensorial database structure. Control or adaptation of the operation of the network with its node devices and couplings is facilitated thereby. The method is suitable particularly for use in supply networks, automated production installations, communication networks, transport networks and logistical networks. The proposed storing allows easy visualisation, depiction and evaluation of operating states of the network and of its node devices.

Abstract: A method and apparatus for automatic recognition of similarities between perturbations in a network, the apparatus includes a memory unit for storing a first data array of multiple perturbation data snapshots each recorded in response to a perturbation observed in the network; a generation unit adapted to generate by machine learning a data model of perturbations trained on the first data array, wherein the trained data model provides a latent vector representation for each of the perturbations; a recording unit adapted to record a perturbation data snapshot if a perturbation is observed during operation of said network and adapted to provide a corresponding second data array for the recorded perturbation data snapshot; and a processing unit adapted to derive a latent vector representation for the observed perturbation from the second data array using the trained data model of perturbations.

Abstract: A method is provided for calculating a relation indicator for a relation between entities based on an optimization procedure. The method combines the strong relational learning ability and the good scalability of the RESCAL model with the linear regression model, which may deal with observed patterns to model known relations. The method may be used to determine relations between objects, for instance entries in a database, such as a shopping platform, medical treatments, production processes, or in the context of the Internet of Things, in a fast and precise manner.

Abstract: Systems and methods are provided for deriving a prediction from existing data by utilizing information extraction and machine learning, wherein both approaches can be optimized independently from each other. Optionally, deductive reasoning may also be combined with information extraction and machine learning and may as well be optimized independently from the other two functionalities. The two or three functionalities may utilize at least one set of data and may (at least partially) process various sets of data. The combined approach may produce significantly improved results, and may be implemented in various technical fields, applications and use cases involving, e.g., data mining or processing of huge amounts of data. The disclosed systems and methods may be applicable for all kinds of technical systems, e.g., medical, genetic research, or industry and automation systems.

Abstract: Systems and methods are provided for deriving a prediction from existing data by utilizing information extraction and machine learning, wherein both approaches can be optimized independently from each other. Optionally, deductive reasoning may also be combined with information extraction and machine learning and may as well be optimized independently from the other two functionalities. The two or three functionalities may utilize at least one set of data and may (at least partially) process various sets of data. The combined approach may produce significantly improved results, and may be implemented in various technical fields, applications and use cases involving, e.g., data mining or processing of huge amounts of data. The disclosed systems and methods may be applicable for all kinds of technical systems, e.g., medical, genetic research, or industry and automation systems.

Abstract: A method, system, and computer software for information retrieval in semantic networks, has the steps of: acquiring a graph of interest, assuming a novel metric regarding the acquired graph, specifying a query node of interest on the obtained graph, calculating a shortest-path distance from the query node of interest to a plurality of other nodes on the acquired graph, obtaining a ranked list of nodes based on the calculated shortest-path distance, and displaying for a user the retrieved information.

Abstract: A method, system, and computer software for information retrieval in semantic networks, has the steps of: acquiring a graph of interest, assuming a novel metric regarding the acquired graph, specifying a query node of interest on the obtained graph, calculating a shortest-path distance from the query node of interest to a plurality of other nodes on the acquired graph, obtaining a ranked list of nodes based on the calculated shortest-path distance, and displaying for a user the retrieved information.