11 results about "Independent vector" patented technology

Methods and systems for image alignment are provided. In one embodiment, a method includes individually aligning candidate alignment target images in an image generated for a sample to corresponding set images of set alignment targets selected to have mutually linearly independent vectors between a position of the set alignment targets and a reference position. The method also includes, for any of the candidate images successfully aligned to their corresponding set images, individually determining coordinates of the reference position from coordinates of the aligned candidate images and their corresponding mutually linearly independent vectors. In addition, the method includes determining final coordinates of the reference position in the image generated for the sample from the individually determined coordinates of the reference position.

The present invention relates to a linear network coding method based on BLS. The source node divides the file to be signed into several file blocks and represents them as a prime domain #imgabs0# k dimensional vectors, which are then augmented to become a set of linearly independent vectors; a subspace generated based on this set of vectors is signed, and a label for the subspace and a signature for each basis vector are generated. The signatures are loaded into a data packet and sent to a downstream node; after receiving the data packet, the intermediate router or the destination node verifies the signature of the data packet from the same source node; the intermediate router linearly combines all verified data packets to form a new data packet and sends it to the downstream node; if the destination node receives a predetermined number of verified data packets, it can parse the original data sent by the source node. The present invention can not only resist pollution attacks in network coding and ensure data integrity and authenticity, but also reduce user computing complexity and ensure secure and efficient data transmission.

The application discloses a kind of multi-node base station traffic prediction methods based on self-organizing graph neural network, belong to space-time traffic prediction technical field, including base station node data processing and influence evaluation: node set subgraph is formed, and the size of influence of adjacent matrix and evaluation node is generated;Base station node reorganization: through mapping matrix, linear combination is carried out to time sequence node, generates linearly independent vector base, and according to influence guide mapping matrix convergence direction;Using part attention aggregation spatial feature: node set is sequentially carried out static graph convolution and dynamic graph convolution and captures spatial connection;In convolution, long short-term memory network is inserted: capture time connection and carry out time series prediction;Finally, standardization is carried out and is generated prediction result by multilayer perception machine.The application uses the above-mentioned one kind of multi-node base station traffic prediction methods based on self-organizing graph neural network, proposes the spatial feature extraction mechanism of multi-node base station traffic, provides effective prediction method for the change trend of base station traffic.

The invention discloses a multi-node base station flow prediction method based on a self-organizing graph neural network, and belongs to the technical field of space-time flow prediction, and the method comprises the steps: processing base station node data and evaluating the influence: carrying out the sub-graphing of a node set, generating an adjacent matrix, and evaluating the node influence; base station node recombination: performing linear combination on time sequence nodes through the mapping matrix to generate a linear independent vector base, and guiding the convergence direction of the mapping matrix according to the influence; gathering spatial features by using partial attention; sequentially carrying out static graph convolution and dynamic graph convolution on a node set to capture spatial relation; interpenetrating a long-short-term memory network in the convolution; capturing a time relation to carry out time sequence prediction; and finally, standardizing and generating a prediction result through a multi-layer perceptron. According to the multi-node base station flow prediction method based on the self-organizing graph neural network, a spatial feature extraction mechanism of the multi-node base station flow is provided, and an effective prediction method is provided for the change trend of the base station flow.

The invention relates to the technical field of artificial intelligence, in particular to a molecular representation distribution external generalization learning method based on annealing noise enhancement and dual vector quantization and application thereof. Extracting node characterization and invariance scores of the molecular graph by using a double-flow encoder to realize preliminary deentanglement of characterization; then, annealing noise enhancement mechanism mixed features are introduced, context dependence is reserved in the initial stage of training, two independent vector quantization experts are utilized to establish exclusive discrete potential spaces for invariant representation and false representation respectively, and the problem of information entanglement of a single codebook is solved; and meanwhile, node-level statistical independence is forcibly realized by utilizing an independence enhancement module, and joint optimization is carried out in combination with an invariant learning strategy. The objective of the invention is to solve the problem of how to realize thorough de-entanglement of invariant representation and false representation of non-Euclidean molecular graph data on a fine-grained node level.

Methods and systems for image alignment are provided. One method includes separately aligning candidate alignment target images in images generated for a specimen to corresponding setup images for setup alignment targets selected to have mutually linearly independent vectors between locations of the setup alignment targets and a reference location. The method also includes, for any of the candidate images successfully aligned to its corresponding setup image, separately determining coordinates of the reference location from coordinates of the aligned candidate images and their corresponding mutually linearly independent vectors. In addition, the method includes determining final coordinates of the reference location in the images generated for the specimen from the separately determined coordinates of the reference location.

Embodiments of the present disclosure relate to identifying replica objects using canonical forms in content creation systems and applications. Systems and methods for determining replica objects in an interactive environment are disclosed. Connectivity information of an object may be used to map a set of three linearly independent vectors corresponding to a transform applied to the object. The three linearly independent vectors may be used to form a canonical form of the first object and the second object to determine whether the first object and the second object are replicas or approximate replicas. The replica object or a copy similar to the replica object may then be deleted from the interaction environment and represented by a common object to which one or more additional transformations are applied.

Methods and systems for image alignment are provided. One method includes separately aligning candidate alignment target images in images generated for a specimen to corresponding setup images for setup alignment targets selected to have mutually linearly independent vectors between locations of the setup alignment targets and a reference location. The method also includes, for any of the candidate images successfully aligned to its corresponding setup image, separately determining coordinates of the reference location from coordinates of the aligned candidate images and their corresponding mutually linearly independent vectors. In addition, the method includes determining final coordinates of the reference location in the images generated for the specimen from the separately determined coordinates of the reference location.

Approaches presented herein provide systems and methods for determining duplicate objects within an interaction environment. Connectivity information for an object may be used to map a set of three linearly independent vectors corresponding to a transform applied to the object. These three linearly independent vectors may be used to form canonical forms of first and second objects to determine whether the first object and the second object are duplicates or near-duplicates. Copies of duplicate or near-duplicate objects may then be deleted from the interaction environment and represented by a common object to which one or more additional transforms are applied.

Methods and systems for image alignment are provided. One method includes separately aligning candidate alignment target images in images generated for a specimen to corresponding setup images for setup alignment targets selected to have mutually linearly independent vectors between locations of the setup alignment targets and a reference location. The method also includes, for any of the candidate images successfully aligned to its corresponding setup image, separately determining coordinates of the reference location from coordinates of the aligned candidate images and their corresponding mutually linearly independent vectors. In addition, the method includes determining final coordinates of the reference location in the images generated for the specimen from the separately determined coordinates of the reference location.

The present invention relates to the field of artificial intelligence technology, and discloses a large language model, a model training method, an apparatus, a medium, a device and a product. The model training method comprises inputting a plurality of text data into a large language model after training convergence to obtain a linearly independent vector matrix; performing singular value decomposition on the linearly independent vector matrix to obtain a singular value matrix; determining the approximate maximum dimension of the linearly independent vector matrix based on the number of singular values ​​greater than a preset cutoff value; optimizing the dimension of the large language model based on the approximate maximum dimension of the linearly independent vector matrix to obtain the actual output vector dimension of the large language model; determining the number of neural network nodes based on the actual output vector dimension of the large language model, and performing model training on the large language model with the determined number of neural network nodes to obtain the large language model after dimension optimization. The present invention realizes the effective optimization of the vector dimension of the large language model, and improves the training and reasoning efficiency of the large language model.