Abstract: A method of identifying and retrieving component digital images for component fault analysis includes generating a known-fault database of digital images of known faults of a previously analyzed component and corresponding remedial actions. The method also includes accessing the known-fault database with a digital image of a current fault of a new component. The method additionally includes comparing the digital image of the current fault with the digital images in the known-fault database based on a computed target characteristic. The method also includes sorting the digital images in the known-fault database in order based on a magnitude of the computed target characteristic for each respective digital image in the known-fault database relative to the digital image of the current fault. The method further includes outputting the sorted digital images to facilitate correlation of the current fault to a particular known fault and identifying the corresponding remedial action.

Abstract: A graphical classification method for classifying graphical structures, said graphical structures comprising nodes defined by feature vectors and having relations between the nodes. The method includes representing the feature vectors and relations as a first graphical representation. The method also includes mapping said first graphical representation into a second graphical representation wherein the mapping comprises using an attention mechanism, said attention mechanism establishes the importance of specific feature vectors dependent on their neighbourhood and the relations between the feature vectors, said mapping transforming the feature vectors of the first graphical representation to transformed feature vectors in the second graphical representation. The method also includes combining the transformed feature vectors to obtain a third combined representation said third combined representation being an indication of the classification of the graphical structure.

Abstract: A method of identifying and retrieving component digital images for component fault analysis includes generating a known-fault database of digital images of known faults of a previously analyzed component and corresponding remedial actions. The method also includes accessing the known-fault database with a digital image of a current fault of a new component. The method additionally includes comparing the digital image of the current fault with the digital images in the known-fault database based on a computed target characteristic. The method also includes sorting the digital images in the known-fault database in order based on a magnitude of the computed target characteristic for each respective digital image in the known-fault database relative to the digital image of the current fault. The method further includes outputting the sorted digital images to facilitate correlation of the current fault to a particular known fault and identifying the corresponding remedial action.

Abstract: A method of training a model, said model being adapted to map a first graphical data structure representation to a second graphical data structure representation, the first graphical data structure representation comprising nodes, with at least one of a plurality of relations between said nodes, the second graphical data structure representation comprising nodes, the mapping comprises using an attention mechanism, wherein said attention mechanism establishes the importance of specific nodes dependent on their neighbourhood and the relations between the nodes, wherein the mapping comprising using a projection kernel to map the nodes of the first graphical structure to nodes of an intermediate representation and using an attention kernel to enact the attention mechanism. The method includes receiving a training data set comprising an output layer and a corresponding input layer. The method also includes training the parameters of the projection kernel and the attention kernel using the training data set.

Abstract: A computer implemented method for classifying molecular structures is provided. The method includes representing the elements and atoms in a molecular structure as nodes and the bonds as relations as a first graphical representation. The method also includes mapping said first graphical representation into a second graphical representation wherein the mapping comprises using an attention mechanism, said attention mechanism establishes the importance of specific feature vectors dependent on their neighbourhood and the relations between the feature vectors, said mapping transforming the feature vectors of the first graphical representation to transformed feature vectors in the second graphical representation. The method also includes combining the transformed feature vectors to obtain a third combined representation. The method also includes mapping said third combined representation to a feature vector indicating properties of the molecular structure.

Abstract: The disclosed system addresses a technical problem tied to computer technology and arising in the realm of computer memory capacity, namely the technical problem of providing a flexible response dialogue system that can be utilised for a variety of different types of dialogue without requiring the system to be specifically trained for each situation. This therefore avoids the need for large amounts of labelled training data for each type of dialogue (each potential conversation flow or subject area for the conversation). The disclosed system solves this technical problem by using semantic similarity to match a user's input to one of a set of predefined inputs (predefined user responses). Various mechanisms are implemented to provide disambiguation in the event of multiple potential matches for the input. By using semantic similarity, the user's response in unconstrained. This therefore provides a user interface that is more user-friendly.

Abstract: A method of mapping a first graphical data structure representation to a second graphical data structure representation, the first graphical data structure representation comprising nodes, with at least one of a plurality of relations between said nodes, the second graphical data structure representation comprising nodes, the mapping comprises using an attention mechanism, wherein said attention mechanism establishes the importance of specific nodes dependent on their neighbourhood and the relations between the nodes.

Abstract: A method of training a model, said model being adapted to map a first graphical data structure representation to a second graphical data structure representation, the first graphical data structure representation comprising nodes, with at least one of a plurality of relations between said nodes, the second graphical data structure representation comprising nodes, the mapping comprises using an attention mechanism, wherein said attention mechanism establishes the importance of specific nodes dependent on their neighbourhood and the relations between the nodes, wherein the mapping comprising using a projection kernel to map the nodes of the first graphical structure to nodes of an intermediate representation and using an attention kernel to enact the attention mechanism. The method includes receiving a training data set comprising an output layer and a corresponding input layer. The method also includes training the parameters of the projection kernel and the attention kernel using the training data set.

Abstract: A computer implemented method for classifying molecular structures is provided. The method includes representing the elements and atoms in a molecular structure as nodes and the bonds as relations as a first graphical representation. The method also includes mapping said first graphical representation into a second graphical representation wherein the mapping comprises using an attention mechanism, said attention mechanism establishes the importance of specific feature vectors dependent on their neighbourhood and the relations between the feature vectors, said mapping transforming the feature vectors of the first graphical representation to transformed feature vectors in the second graphical representation. The method also includes combining the transformed feature vectors to obtain a third combined representation. The method also includes mapping said third combined representation to a feature vector indicating properties of the molecular structure.

Abstract: A graphical classification method for classifying graphical structures, said graphical structures comprising nodes defined by feature vectors and having relations between the nodes. The method includes representing the feature vectors and relations as a first graphical representation. The method also includes mapping said first graphical representation into a second graphical representation wherein the mapping comprises using an attention mechanism, said attention mechanism establishes the importance of specific feature vectors dependent on their neighbourhood and the relations between the feature vectors, said mapping transforming the feature vectors of the first graphical representation to transformed feature vectors in the second graphical representation. The method also includes combining the transformed feature vectors to obtain a third combined representation said third combined representation being an indication of the classification of the graphical structure.

Abstract: A method of mapping a first graphical data structure representation to a second graphical data structure representation, the first graphical data structure representation comprising nodes, with at least one of a plurality of relations between said nodes, the second graphical data structure representation comprising nodes, the mapping comprises using an attention mechanism, wherein said attention mechanism establishes the importance of specific nodes dependent on their neighbourhood and the relations between the nodes.

Abstract: Embodiments described herein provide a more flexible, effective, and computationally efficient means for determining multiple intents within a natural language input. Some methods rely on specifically trained machine learning classifiers to determine multiple intents within a natural language input. These classifiers require a large amount of labelled training data in order to work effectively, and are generally only applicable to determining specific types of intents (e.g., a specifically selected set of potential inputs). In contrast, the embodiments described herein avoid the use of specifically trained classifiers by determining inferred clauses from a semantic graph of the input. This allows the methods described herein to function more efficiently and over a wider variety of potential inputs.

Abstract: The disclosed system addresses a technical problem tied to computer technology and arising in the realm of computer memory capacity, namely the technical problem of providing a flexible response dialogue system that can be utilised for a variety of different types of dialogue without requiring the system to be specifically trained for each situation. This therefore avoids the need for large amounts of labelled training data for each type of dialogue (each potential conversation flow or subject area for the conversation). The disclosed system solves this technical problem by using semantic similarity to match a user's input to one of a set of predefined inputs (predefined user responses). Various mechanisms are implemented to provide disambiguation in the event of multiple potential matches for the input. By using semantic similarity, the user's response in unconstrained. This therefore provides a user interface that is more user-friendly.

Abstract: Embodiments described herein provide a more flexible, effective, and computationally efficient means for determining multiple intents within a natural language input. Some methods rely on specifically trained machine learning classifiers to determine multiple intents within a natural language input. These classifiers require a large amount of labelled training data in order to work effectively, and are generally only applicable to determining specific types of intents (e.g., a specifically selected set of potential inputs). In contrast, the embodiments described herein avoid the use of specifically trained classifiers by determining inferred clauses from a semantic graph of the input. This allows the methods described herein to function more efficiently and over a wider variety of potential inputs.

Abstract: Method of processing an image of the skin is disclosed. The method comprises the receipt of skin image data, the generation of simulated images with artificial transformation and the analysis of the simulated images to form a vector from extracted features.

Abstract: Method of processing an image of the skin is disclosed. The method comprises the receipt of skin image data, the generation of simulated images with artificial transformation and the analysis of the simulated images to form a vector from extracted features.