A method of integrating a device into a factory comprises storing a factory data model describing the factory, the factory data model being a graph of nodes connected by edges. A device data model is stored describing the device, the device data model being a graph of nodes connected by edges. A graph neural network is used to compute, for each node of the factory data model and each node of the device data model, an embedding vector representing a position of the node in a multi-dimensional space. For each node of the device data model, a mapping to a node of the factory data model is computed by finding a node of the factory data model which is closest to the node of the device data model in the multi-dimensional space

Factory device integration

The invention discloses an anti-interference signal identification method and device, computer equipment and a storage medium. According to the method, the neural networks are trained by shielding partial data in the signal instances, and each neural network corresponds to one label, so that each neural network can accurately predict shielded parts of the signal instances with the same label, andmeanwhile, the shielded parts of the signal instances with other labels are difficult to predict; part of the to-be-identified signal is shielded, and the shielded part of the to-be-identified signalis predicted by using each neural network; and the to-be-identified signal is identified as a label corresponding to the neural network with the most accurate shielded part. The method solves the problems that a traditional intelligent signal identification method is uninterpretable, is easily interfered by external noise and is low in robustness. The method has the advantages that the mapping relation between the internal data of the instance signals is established, the method has practical physical significance and interpretability, and the anti-interference performance of the identificationmethod is greatly improved.

Anti-interference signal identification method and device, computer equipment and storage medium

A method of generating a neural network includes iteratively performing operations including generating, for each neural network of a population, a matrix representation. The matrix representation of a particular neural network includes rows of values, where each row corresponds to a set of layers of the particular neural network and each value specifies a hyperparameter of the set of layers. The operations also include providing the matrix representations as input to a relative fitness estimator that is trained to generate estimated fitness data for neural networks of the population. The estimated fitness data are based on expected fitness of neural networks predicted by the relative fitness estimator. The operations further include generating, based on the estimated fitness data, a subsequent population of neural networks. The method also includes, when a termination condition is satisfied, outputting data identifying a neural network as a candidate neural network.

Automated neural network generation using fitness estimation

The present invention relates to generating and training neural networks for application in numerous fields including object or event recognition in images including visual sequences There is provided a computerised method of generating a neural network (NN), comprising generating successive candidate NNs (310, 545) using an optimisation algorithm (530), each NN having a number of connected blocks of layers (205), the layers having a plurality of neurons with connections having associated weights Each block comprises fixed and variable architectural parameters (210X, 210Y), the or each variable architectural parameter being determined by an optimisation algorithm Each candidate NN is trained using training data in order to update the weights of the candidate NN (320), and a fitness function score of the trained candidate NN is determined using validation data (330) If there is a block having the same architectural parameters from a previously trained candidate NN, the weights associated with layers of said block are inherited prior to training and fitness score determination (425)

Image classification, generation and application of neural networks

The present application discloses a neural network construction method, an image processing method and devices in the field of computer vision in the field of artificial intelligence. The neural network construction method comprises: determining a search space and a plurality of construction units; stacking the plurality of construction units to obtain a search network, wherein the search network is a neural network for neural architecture search; optimizing, in the search space, the architecture of the construction units within the search network, so as to obtain optimized construction units, wherein in an optimization process, the search space is gradually reduced, the number of construction units is gradually increased, and the reduction of the search space and the increase of the number of construction units enable a graphics memory consumed in the optimization process to be within a preset range; and constructing the target neural network according to the optimized construction units. The present application is able to construct a neural network which better satisfies application requirements in the case where graphics memory resources are ensured.

Moore Sherry

Papers

Optimizing neural network architectures

Augmenting neural networks