13 results about "Artificial neural network" patented technology

A machine learning system is provided to enhance various aspects of machine learning models. In some aspects, a substantially photorealistic three-dimensional (3D) graphical model of an object is accessed and a set of training images of the 3D graphical mode are generated, the set of training images generated to add imperfections and degrade photorealistic quality of the training images. The set of training images are provided as training data to train an artificial neural network.

An intelligent (self-learning) sensor-aware and / or context-aware subsystem comprising (i) a System-on-a-Chip (SoC), (ii) a radio transceiver, (iii) a microphone, (iv) a voice processing module, (v) a (bio-inspired) neuromorphic event camera or a hyperspectral camera, (vi) a digital personal assistant (DPA), (vii) a first set of computer implemental instructions in artificial neural networks (ANN) (which may include a transformer model / diffusion model or Poisson flow generative model++ (PFGM++)), (viii) a second set of computer implementable instructions to analyze and interpret contextual data and (ix) an autonomous artificial intelligence (AI) agent is disclosed.

Various techniques are provided for providing neural networks with increased efficiency. In one example, a system includes a first artificial neural network (ANN), a second ANN, and a logic device. The first ANN is configured to receive a first plurality of data inputs associated with a data stream and process the first data inputs to generate a first inference output after a first latency. The second ANN is configured to receive a second plurality of data inputs associated with the data stream and process the second data inputs to generate a second inference output after a second latency less than the first latency. The logic device is configured to receive the second inference output before the first inference output is generated. Additional systems and methods are also provided.

A method for converting an input image (Iin) having a first dynamic range (Δ1), into an output image (Iout), having a second dynamic range (Δ2) distinct from the first dynamic range, the input image being represented by an input luminance component (Yin) comprising first input pixel values, and at least one input chrominance component (Cbin, Crin) comprising second input pixel values, the output image being represented by an output luminance component (Yout) comprising first output pixel values, and at least one output chrominance component (Cbout, Crout) comprising second output pixels values, the method comprising the steps of: a) determining at least one statistical value (sin) associated with the input image, based on at least part of the first input pixel values, b) determining each first output pixel value based on a corresponding first input pixel value and said at least one statistical value, c) applying on first input nodes (115, 116, 117) of an artificial neural network (CNN1), the second input pixel values, respectively, and applying on at least one second node of the artificial neural network, the at least one statistical value, the artificial neural network being configured to provide on respective output nodes (111,112), the second output pixel values. A corresponding device (1) for converting an input image into an output image is also described.

The invention provides a system and method for training artificial neural networks for solving multiple tasks simultaneously, wherein the artificial neural network comprises at least one capsule layer. The invention also provides a system and a method for solving multiple tasks simultaneously, wherein the artificial neural network comprises at least one capsule layer. The invention further provides additional connected aspects.

The present technology discloses the development of a trained learning model for forecasting system using artificial neural networks (ANNs) along with genetic algorithms (GA) to predict the compressive and flexural strength of engineered bamboo products. The model processes mechanical attributes including binder properties, fiber content, and curing duration that is to be compares the results with the database of the system. Due to the significant cons of manual testing in engineered bamboo products, including being time-consuming, resource-intensive, and limited scalability, the utility model provides an efficient and cost-effective alternative for determining material strength. Furthermore, the optimized testing parameters generated by the model can be stored and applied in subsequent testing of engineered bamboo products.

This invention discloses an online method for judging the operational health status of the central valve under throttling heating boundary conditions. By extracting information from characteristic parameters under throttling conditions, this invention comprehensively integrates and utilizes multi-source information, sequentially extracting multi-dimensional fault state information across categories for individual characteristic parameters, ensuring the accuracy and completeness of fault state information extraction. Furthermore, this invention achieves the identification and prediction of fault state-sensitive physical quantities through dimensionality reduction decomposition of the array matrix. Combining artificial neural network sample training with targeted focusing on expert databases, this invention can achieve high-precision evaluation of the operational health status of the central valve and real-time online judgment of its operational health status under throttling heating boundary conditions, while significantly reducing the amount of sample data used. This is of great significance for promoting the safe and reliable operation of heating systems under partial load conditions.

A voice signal estimation apparatus includes: a microphone encoder that receives a microphone input signal including an echo signal and a user's voice signal, converts it into first input information, and outputs the information; a far-end signal encoder that receives a far-end signal, converts it into second input information, and outputs the information; and an attention unit outputting weight information by applying an attention mechanism to the first and second input information. The apparatus further includes a pre-learned first artificial neural network receiving third input information, which is the sum of the weight information and the second input information, and outputting first output information including mask information for estimating the voice signal from the second input information. A voice signal estimator outputs an estimated voice signal based on the first output information and the second input information.

This invention provides a vehicle re-identification method based on dynamic convolutional Transformers. Unlike methods where different local regions share a single convolutional kernel, this invention uses a single convolutional kernel pool for each local region. A fully connected artificial neural network learns a set of coefficients from each local region. The convolutional kernels in the pool are then linearly fused using these coefficients to obtain dedicated convolutional kernels for each local region, which are used to learn the features of that region. Therefore, this invention can adaptively learn the corresponding convolutional kernels based on the representational characteristics of each local region, enabling better learning of local features in vehicle images and thus improving vehicle re-identification performance.

This invention relates to an air data indication and calibration device (1) and method for a vertical takeoff and landing (VTOL) aircraft, specifically a helicopter (50), for providing airspeed information and altitude information of the VTOL aircraft. The VTOL aircraft includes: a pitot tube device (51) for determining stagnation pressure at the location of the pitot tube device (51); and a static pressure orifice device (52) for determining static pressure at the location of the static pressure orifice device (52). The air data indication device (1) includes an airspeed and altitude determination module (2) for determining the airspeed and altitude of the VTOL aircraft in real time based on flight data using a regressor (3) obtained by training an artificial neural network through training data.

The invention relates to the technical field of structural health detection, and particularly discloses a composite material impact positioning method based on an optical fiber sensor, a medium and equipment. According to the method, the optical fiber sensor is embedded into a composite material, an impact response signal in the material is monitored in real time, and corresponding signals of all FBG sensors serve as reference data; and then preprocessing is carried out, Fourier transform is utilized to obtain a frequency domain signal, the characteristic quantity of related energy is calculated according to the frequency domain signal, and accurate positioning of an impact position is realized according to a weighted centroid algorithm. According to the method, the sampling frequency is far lower than that of a time positioning method, and the data size is far smaller than that of an artificial neural grid method, so that the impact position can be accurately positioned under low-frequency and small-data samples, the test period is effectively shortened, the positioning accuracy is improved, and the method has universality.

A method, a computerized apparatus and a computer program product for parking slot detection. The method comprises obtaining an elevated perception map of a surrounding area around a vehicle. Each pixel in the elevated perception map is associated with a predetermined relative location to the vehicle. The elevated perception map comprises a plurality of functional layers. Values of pixels at different layers indicate an infrastructure segment or object located at corresponding relative locations to the vehicle. The method further comprises performing parking slot object detection in the elevated perception map. The parking slot object detection is performed using an Artificial Neural Network (ANN) to obtain one or more detected parking slot objects. The one or more detected parking slot objects are provided to autonomous driving systems and utilized to autonomously park vehicles in vacant parking slots that are selected therefrom.

A computer implemented method is provided for multimodal data classification with brain-inspired unsupervised learning, and a neuromorphic computing hardware structure for implementing the method. In a preferred embodiment, the method comprises the steps of: training with unsupervised learning based on a multimodal training dataset each of a plurality of Artificial Neural Networks (ANNs); training with unsupervised learning based on the multimodal training dataset a multimodal association between the ANNs to generate a plurality of bidirectional lateral connections between co-activated Best Matching Units (BMUs); labeling the neurons of each of the at least two ANNs with a divergence algorithm; and electing a global BMU with a convergence algorithm.