Si desitges distingir els teus productes, serveis o tots dos dels d'una altra empresa, és possible que necessitis una marca o nom comercial. Descobreix què són, en què consisteix el seu procediment de registri i què implica.
Información sobre los plazos de presentación de solicitudes de transformación de marcas de la Unión Europea en marca nacional española. Más información
Si tens un nou dispositiu, producte o procediment que resolgui un problema tècnic o tingui un avantatge pràctic, existeixen diferents formis de protegir-ho a Espanya i en altres països. Descobreix com fer-ho.
La teva innovació resideix en l'estètica, l'ornamentació o l'aparença del teu producte? Protegeix-la mitjançant un disseny industrial. Descobreix quins drets confereix el registri i com realitzar la tramitació.
Els patents publicades a tot el món són una valuosa font d'informació científica, tècnica i comercial.
reembolso del 75% del coste de Búsquedas e Informes Tecnológicos de Patentes. Más información*
Si ets emprenedor/a o una empresa i vols potenciar i millorar la rendibilitat del teu negoci protegint de forma adequada els actius intangibles de la teva organització, en aquest espai trobaràs el necessari.
29
resultados
Última actualización
06/10/2024 [07:43:00]
Resumen de: US2024330685A1
The present application relates to a computer-implemented method for an improved technique for optimising the loss function during deep learning. The method includes receiving a training data set comprising a plurality of data items, initialising weights of at least one neural network layer of the ML model, and training, using an iterative process, the at least one neural network layer of the ML model by inputting, into the at least one neural network layer, the plurality of data items, processing the plurality of data items using the at least one neural network layer and the weights, optimising a loss function of the weights by simultaneously minimising a loss value and a loss sharpness using weights that lie in a neighbourhood having a similar low loss value, wherein the neighbourhood is determined by a geometry of a parameter space defined by the weights of the ML model, and updating the weights of the at least one neural network layer using the optimised loss function.
Resumen de: WO2024205617A1
System and method of classification of manufacturing defects and anomaly detection based on a neural network model applying physical measurement data. The system includes a graph engine and a graph neural network (GNN). The graph engine generates a graph of measurement points, a measurement matrix, and weight matrix of connected node distances. The GNN model includes an encoder that encodes the measurement matrix and the weight matrix to generate a latent node representation, from which a decoder determines node reconstructions. Unsupervised training converges by minimizing node reconstruction loss, the reconstruction performed using a decoder that decodes the latent node representation. Supervised training converges by minimizing reconstruction of binary labels of annotated measurement inputs, the reconstruction performed by a softmax layer that translates the latent node representation.
Resumen de: US2024330679A1
A method for making predictions pertaining to entities represented within a heterogeneous graph includes: identifying, for each node in the heterogeneous graph structure, a set of node-target paths that connect the node to a target node; assigning, to each of the node-target paths identified for each node, a path type identifier indicative of a number of edges and corresponding edge types in the associated node-target path; and extracting a semantic tree from the heterogeneous graph structure. The semantic tree includes the target node as a root node and defines a hierarchy of metapaths that each individually correspond to a subset of the node-target paths in the heterogeneous graph structure assigned to a same path type identifier. The semantic tree is encoded, using one or more neural networks by generating a metapath embedding corresponding to each metapath in the semantic tree. Each of the resulting metapath embeddings encodes aggregated feature-label data for nodes in the heterogeneous graph structure corresponding to the path type identifier corresponding to the metapath associated with the metapath embedding. A label is predicted for the target node in the heterogeneous graph structure based on the set of metapath embeddings.
Resumen de: US2024330681A1
A device for optimizing parameters of a deep neural network is included in an integrated circuit apparatus. The integrated circuit apparatus includes a general interconnection interface and other processing apparatus. A computing apparatus interacts with other processing apparatus to jointly complete a computing operation specified by a user. The integrated circuit apparatus further includes a storage apparatus. The storage apparatus is connected to the computing apparatus and other processing apparatus, respectively. The storage apparatus is used for data storage of the computing apparatus and other processing apparatus.
Resumen de: WO2024205909A1
A method for making predictions includes identifying, for each node in the heterogeneous graph structure, a set of node-target paths that connect the node to a target node; assigning, to each of the node-target paths, a path type identifier indicative of a number of edges and corresponding edge types in the associated node-target path; and extracting a semantic tree from the heterogeneous graph structure. The semantic tree includes the target node as a root node and defines a hierarchy of metapaths that each correspond to a subset of the node-target paths in the heterogeneous graph structure assigned to a same path type identifier. The semantic tree is encoded by generating a metapath embedding corresponding to each metapath in the semantic tree. A label is predicted for the target node in the heterogeneous graph structure based on the set of metapath embeddings.
Resumen de: US2024331342A1
Systems and methods are provided for determining an occlusion class indicator corresponding to an occlusion image. This can include acquiring the occlusion image of an occlusion of a human subject by an image capture device, applying one or more computer-implemented occlusion classification neural networks to the occlusion image to determine the class indicator of the occlusion of the human subject. The occlusion classification neural networks are trained for classification using an occlusion training dataset including a plurality of occlusion training examples being pre-classified into one three occlusion classes, each class being attributed a numerical value. The occlusion class indicator determined by the occlusion classification neural network includes a numeric value within a continuous range of values that can be bounded by the values corresponding to the second and third occlusion classes.
Resumen de: US2024333927A1
The present disclosure relates to video encoding or decoding and, more specifically, to an apparatus and a method for applying an artificial neural network (ANN) to video encoding or decoding. The apparatus and the method of the present disclosure are characterized by applying a CNN-based filter to a first picture and at least one of a quantization parameter map and a block partition map to output a second picture.
Resumen de: US2024333924A1
The present disclosure relates to video encoding or decoding and, more specifically, to an apparatus and a method for applying an artificial neural network (ANN) to video encoding or decoding. The apparatus and the method of the present disclosure are characterized by applying a CNN-based filter to a first picture and at least one of a quantization parameter map and a block partition map to output a second picture.
Resumen de: US2024333926A1
The present disclosure relates to video encoding or decoding and, more specifically, to an apparatus and a method for applying an artificial neural network (ANN) to video encoding or decoding. The apparatus and the method of the present disclosure are characterized by applying a CNN-based filter to a first picture and at least one of a quantization parameter map and a block partition map to output a second picture.
Resumen de: US2024333925A1
The present disclosure relates to video encoding or decoding and, more specifically, to an apparatus and a method for applying an artificial neural network (ANN) to video encoding or decoding. The apparatus and the method of the present disclosure are characterized by applying a CNN-based filter to a first picture and at least one of a quantization parameter map and a block partition map to output a second picture.
Resumen de: US2024331041A1
A user-described virtual environment method, system, and apparatus obtains a representation of an object and receives a natural language-based communication from a user requesting that a computer-implemented system embody the object within a virtual environment that is described by the user. The natural language description of the virtual environment is interpreted by applying a computer-implemented trained neural network A video stream that embodies the object within a computer-generated virtual environment that is in accordance with the user-described virtual environment is generated by applying a trained neural network and then delivered to the user. The user may then describe desired modifications to the virtual environment and a second video stream is generated in accordance with the desired modifications.
Resumen de: US2024330645A1
A computer-implemented method includes receiving, at a neural network, input data indicating at least video data and natural language data, in response to meeting a convergence threshold of the neural network utilizing the input data, outputting one or more patterns associated with the input data to a cognitive architecture, wherein the cognitive architecture is in communication with a symbolic framework that includes a knowledge graph database and the symbolic framework is configured to identify contextual information of the one or more patterns received from the neural network utilizing at least the knowledge graph database, in response to the symbolic framework communicating the contextual information with the neural network, embedding the neural network with the contextual information of the knowledge graph dataset and outputting a recommendation indicating information associated with at least the input data utilizing an embedded neural network.
Resumen de: US2024320986A1
In various examples, live perception from sensors of an ego-machine may be leveraged to detect objects and assign the objects to bounded regions (e.g., lanes or a roadway) in an environment of the ego-machine in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute outputs—such as output segmentation masks—that may correspond to a combination of object classification and lane identifiers. The output masks may be post-processed to determine object to lane assignments that assign detected objects to lanes in order to aid an autonomous or semi-autonomous machine in a surrounding environment.
Resumen de: US2024323203A1
Aspects of the disclosure relate to enhancing hybrid traditional neural networks with liquid neural networks for cyber security and offense protection. A computing platform may receive a request to access enterprise organization data. The computing platform may compare the current request to previous requests to determine whether a similar request was previously processed. If a similar request was not previously processed, the computing platform may flag the request as a threat and may analyze the request. The computing platform may extract data from the request and may use the extracted data to generate rules, threat detection algorithms, and training models. The computing platform may use the rules, threat detection algorithms, and training models to train a deep learning neural network to identify and handle threats to an enterprise organization.
Resumen de: US2024320686A1
A third-party service may be used to assist entities in responding to requests of users by determining a suggested resource corresponding to a received communication. The third party service may receive a request from a first entity, such as via an application programming interface request, that includes a message in a conversation. A conversation feature vector may be computed by processing the message with a first neural network. A suggested resource may be determined using the conversation feature vector. The third-party service may then return the suggested resource for use in the conversation. The third-party service may similarly be used to assist other entities in responding to requests of users.
Resumen de: US2024320455A1
To suppress an increase in processing time due to a load of inference processing while improving reading accuracy by the inference processing of machine learning. An optical information reading device includes a processor including: an inference processing part that inputs a code image to a neural network and executes inference processing of generating an ideal image corresponding to the code image; and a decoding processing part that executes first decoding processing of decoding the code image and second decoding processing of decoding the ideal image generated by the inference processing part. The processor executes the inference processing and the first decoding processing in parallel, and executes the second decoding processing after completion of the inference processing.
Resumen de: US2024320298A1
Methods of implementing a sparse submanifold convolution using a neural network accelerator. The methods include: receiving, at the neural network accelerator, an input tensor in a sparse format; performing, at the neural network accelerator, for each position of a kernel of the sparse submanifold convolution, a 1×1 convolution between the received input tensor and weights of filters of the sparse submanifold convolution at that kernel position to generate a plurality of partial outputs; and combining appropriate partial outputs of the plurality of partial outputs to generate an output tensor of the sparse submanifold convolution in sparse format.
Resumen de: WO2024195280A1
Problem To input the feature of causal relation between words into a causal relation extraction model and perform machine learning. Solution A learning device 10 acquires, in correspondence with individual words included in the text of training data 135, third correspondence information that is generated on the basis of first correspondence information in which words and vectors are associated on the basis of word embedding and second correspondence information in which words and vectors are associated on the basis of the correlation of a word pair between a first word indicating a cause and a second word indicating a result that is based on the cause indicated by the first word. The learning device 10 uses the acquired third correspondence information to execute training of a neural network that performs natural language processing.
Resumen de: US2024320337A1
A neural network (NN) configuration parameter training and deployment method and apparatus are disclosed. The method and the apparatus include searching for simulated attacked NN configuration parameters on a basis of NN configuration parameters, so that the attacked NN configuration parameters move in a direction of maximal divergence from an NN output result corresponding to the NN configuration parameters; taking a difference in an NN output result between the current NN configuration parameters and the attacked NN configuration parameters as a robustness loss function which serves as a part of a total loss function; and finally, optimizing the NN configuration parameters on a basis of the total loss function. Especially for sub-threshold and mixed-signal circuits with ultra-low power consumption, the solution can solve a problem of perturbations of configuration parameters caused by device mismatch, and achieve the technical effect of low-cost and high-efficiency deployment of parameters of NN accelerators.
Resumen de: US2024314452A1
Disclosed is an imaging system with an image sensor; and at least one processor configured to obtain image data read out by the image sensor; obtain information indicative of a gaze direction of a given user; and utilise at least one neural network to perform demosaicking on an entirety of the image data; identify a gaze region and a peripheral region of the image data, based on the gaze direction of the given user; and apply at least one image restoration technique to one of the gaze region and the peripheral region of the image data.
Resumen de: US2024312184A1
Methods and systems for training one or more neural networks for transcription and for transcribing a media file using the trained one or more neural networks are provided. One of the methods includes: segmenting the media file into a plurality of segments; inputting each segment, one segment at a time, of the plurality of segments into a first neural network trained to perform speech recognition; extracting outputs, one segment at a time, from one or more layers of the first neural network; and training a second neural network to generate a predicted-WER (word error rate) of a plurality of transcription engines for each segment based at least on outputs from the one or more layers of the first neural network.
Resumen de: US2024311267A1
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a surrogate neural network configured to determine a predicted performance measure of a hardware accelerator having a target hardware configuration on a target application. The trained instance of the surrogate neural network can be used. in addition to or in place of hardware simulation, during a search process for determining hardware configurations for application-specific hardware accelerators. i.e., hardware accelerators on which one or more neural networks can be deployed to perform one or more target machine learning tasks.
Resumen de: CN117597691A
Systems, apparatuses, and methods may provide techniques to prefetch compressed data and a sparsity bitmap from a memory to store the compressed data in a decode buffer, where the compressed data is associated with a plurality of tensors, where the compressed data is in a compressed format. The technique aligns the compressed data with the sparsity bitmap to generate decoded data, and provides the decoded data to a plurality of processing elements.
Resumen de: US2024303837A1
A neural network apparatus includes one or more processors comprising: a controller configured to determine a shared operand to be shared in parallelized operations as being either one of a pixel value among pixel values of an input feature map and a weight value among weight values of a kernel, based on either one or both of a feature of the input feature map and a feature of the kernel; and one or more processing units configured to perform the parallelized operations based on the determined shared operand.
Nº publicación: US2024303328A1 12/09/2024
Solicitante:
IRDETO B V [NL]
Irdeto B.V
Resumen de: US2024303328A1
Disclosed implementations include a method of detecting attacks on Machine Learning (ML) models by applying the concept of anomaly detection based on the internal state of the model being protected. Instead of looking at the input or output data directly, disclosed implementation look at the internal state of the hidden layers of a neural network of the model after processing of data. By examining how different layers within a neural network model are behaving an inference can be made as to whether the data that produced the observed state is anomalous (and thus possibly part of an attack on the model).
BOPI
Sede Electrónica
