Absstract of: US2024355109A1
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining one or more neural network architectures of a neural network for performing a video processing neural network task. In one aspect, a method comprises: at each of a plurality of iterations: selecting a parent neural network architecture from a set of neural network architectures; training a neural network having the parent neural network architecture to perform the video processing neural network task, comprising determining trained values of connection weight parameters of the parent neural network architecture; generating a new neural network architecture based at least in part on the trained values of the connection weight parameters of the parent neural network architecture; and adding the new neural network architecture to the set of neural network architectures.
Absstract of: US2024354559A1
A mechanism is described for facilitating smart distribution of resources for deep learning autonomous machines. A method of embodiments, as described herein, includes detecting one or more sets of data from one or more sources over one or more networks, and introducing a library to a neural network application to determine optimal point at which to apply frequency scaling without degrading performance of the neural network application at a computing device.
Absstract of: US2024354595A1
The present disclosure describes methods and systems for quantifying certainty for a prediction based on a knowledge graph. The method includes receiving a target triple and a knowledge graph comprising a set of structured data and a set of certainty scores for the structured data; converting the target triple to an embeddings space according to neighborhood sampling by a neural network, wherein the embeddings space includes a set of point coordinates; generating a plausibility prediction for the target triple using a scoring function; repeating converting the target triple to the embedding space and generating another plausibility prediction for the target triple N times with dropouts to obtain N plausibility scores for the target triple, wherein N is an integer larger than one; generating a predicted plausibility score and a certainty score for the target triple; and outputting the predicted plausibility score and the certainty score.
Absstract of: US2024354568A1
A computer-implemented technique for deep distilling is disclosed. The technique includes obtaining training samples for training an artificial neural network: determining multiple sub concepts within the training samples such that a minimum number of linearly separable sub concept regions are formed: processing the sub concepts to obtain neurons that form an output of the neural network: organizing the neurons into one or more groups with similar connectivity patterns: and interpreting the neurons as implementing logical functions.
Absstract of: US2024354931A1
A vision analytics and validation (VAV) system for providing an improved inspection of robotic assembly, the VAV system comprising a trained neural network three-way classifier, to classify each component as good, bad, or do not know, and an operator station configured to enable an operator to review an output of the trained neural network, and to determine whether a board including one or more “bad” or a “do not know” classified components passes review and is classified as good, or fails review and is classified as bad. In one embodiment, a retraining trigger to utilize the output of the operator station to train the trained neural network, based on the determination received from the operator station.
Absstract of: US2024355091A1
Embodiments include techniques to determine a set of credit risk assessment data samples, generate local credit risk assessment attributions for the set of credit risk assessment samples, and normalize each local credit risk assessment attribution of the local credit risk assessment attributions. Further, embodiments techniques to compare each pair of normalized local credit risk assessment attributions and assign a rank distance thereto proportional to a degree of ranking differences between the pair of normalized local credit risk assessment attributions. The techniques also include applying a K-medoids clustering algorithm to generate clusters of the local risk assessment attributions, generating global attributions, and determining insights for the neural network based on the global attributions.
Absstract of: US2024346654A1
The present system provides methods and systems of detecting lung abnormalities in chest x-ray images using at least two neural networks.
Absstract of: US2024346655A1
The present system provides methods and systems of detecting lung abnormalities in chest x-ray images using at least two neural networks.
Absstract of: US2024347164A1
An estimate of a functional capacity such as VO2Max is made by applying the vital signs of a monitored human to a trained encoding neural network producing a cardio profile vector. The vector is applied to a trained functional capacity (VO2Max) neural network to estimate the functional capacity. Once estimated, an action is taken.
Absstract of: US2024347061A1
Training and/or utilizing a single neural network model to generate, at each of a plurality of assistant turns of a dialog session between a user and an automated assistant, a corresponding automated assistant natural language response and/or a corresponding automated assistant action. For example, at a given assistant turn of a dialog session, both a corresponding natural language response and a corresponding action can be generated jointly and based directly on output generated using the single neural network model. The corresponding response and/or corresponding action can be generated based on processing, using the neural network model, dialog history and a plurality of discrete resources. For example, the neural network model can be used to generate a response and/or action on a token-by-token basis.
Absstract of: US2024342909A1
Various embodiments of the technology described herein generally relate to systems and methods for trajectory optimization with machine learning techniques. More specifically, certain embodiments relate to using neural networks to quickly predict optimized robotic arm trajectories in a variety of scenarios. Systems and methods described herein use deep neural networks to quickly predict optimized robotic arm trajectories according to certain constraints. Optimization, in accordance with some embodiments of the present technology, may include optimizing trajectory geometry and dynamics while satisfying a number of constraints, including staying collision-free and minimizing the time it takes to complete the task.
Absstract of: WO2024215112A1
Provided is a computer-readable storage medium for storing one or more programs, the one or more programs, when executed by a processor of an electronic device, being configured to identify the number of one or more first software applications executed in the electronic device. The one or more programs, when executed by the processor of the electronic device, may be configured to provide, to a neural network in response to the number that has reached a reference number, session information comprising first data representing the one or more first software applications and second data representing time information. The one or more programs, when executed by the processor of the electronic device, may be configured to include instructions for the electronic device to acquire, from the neural network, at least one second software application identified on the basis of the session information.
Absstract of: US2024346298A1
A parallel convolutional neural network is provided. The CNN is implemented by a plurality of convolutional neural networks each on a respective processing node. Each CNN has a plurality of layers. A subset of the layers are interconnected between processing nodes such that activations are fed forward across nodes. The remaining subset is not so interconnected.
Absstract of: US2024346332A1
Aspects discussed herein may relate to methods and techniques for embedding constrained and unconstrained optimization programs as layers in a neural network architecture. Systems are provided that implement a method of solving a particular optimization problem by a neural network architecture. Prior systems required use of external software to pre-solve optimization programs so that previously determined parameters could be used as fixed input in the neural network architecture. Aspects described herein may transform the structure of common optimization problems/programs into forms suitable for use in a neural network. This transformation may be invertible, allowing the system to learn the solution to the optimization program using gradient descent techniques via backpropagation of errors through the neural network architecture. Thus these optimization layers may be solved via operation of the neural network itself.
Absstract of: GB2629048A
A sock sensor obtains physiological and/or motion data of a user wearing a sock 110, sequenced time series data is processed using a machine learning classifier 122 to generate classification data to predict one of a plurality of categories which represent the state of stress of the person. The states of stress of the person may include pain or anxiety. Preferably the physiological sensor senses electrodermal (EDA) activity of the skin and the motion sensor is an accelerometer. Preferably, the processing of the time series data in a sequence generates a 2D image (fig 4) that represents relationships between the data in the sequence, and this is achieved using a convolutional neural network (CNN) to generate the classification data. The classification data may have a score for each category of the plurality of categories. An alert maybe created based on the stress category. Also, a method of monitoring a person via a wearable sensor is disclosed and a computer implemented method to detect whether a person is exhibiting a heightened physiological response.
Absstract of: EP4446941A2
Methods and apparatus for discrimitive semantic transfer and physics-inspired optimization in deep learning are disclosed. A computation training method for a convolutional neural network (CNN) includes receiving a sequence of training images in the CNN of a first stage to describe objects of a cluttered scene as a semantic segmentation mask. The semantic segmentation mask is received in a semantic segmentation network of a second stage to produce semantic features. Using weights from the first stage as feature extractors and weights from the second stage as classifiers, edges of the cluttered scene are identified using the semantic features.
Absstract of: EP4446946A2
A method of generating a controller (60) for a continuous process. The method includes receiving from a storage memory (26) off-line stored values of one or more controlled variables and one or more manipulated variables of the continuous process over a plurality of time points. The off-line stored values are used to train a first neural network to operate as a predictor (58) of the controlled variables. Then, the method includes training a second neural network to operate as a controller of the continuous process using the first neural network after it was trained to operate as the predictor for the continuous process and employing the second neural network as a controller of the continuous process.
Absstract of: KR20240149684A
인공 신경망 기반의 질의 처리 장치 및 방법이 개시된다. 개시되는 일 실시예에 따른 질의 처리 장치는, 각 분야 별로 배경 지식을 획득하고, 획득한 배경 지식을 전처리 하여 기 설정된 기준 길이의 문장들을 생성하는 전처리 모듈 및 제1 언어 처리 모델을 포함하고, 기준 길이의 문장을 복수 개의 청크 단위로 분할하여 제1 언어 처리 모델로 입력하며, 제1 언어 처리 모델을 통해 각 청크 단위에 대해 문장 임베딩 벡터를 생성하고, 생성한 문장 임베딩 벡터를 색인하여 신경망 데이터베이스에 저장하는 제1 언어 처리 모듈을 포함하며, 제1 언어 처리 모듈은, 질의가 입력되는 경우, 질의를 제1 언어 처리 모델에 입력하여 질의에 대한 문장 임베딩 벡터를 생성하고, 질의에 대한 문장 임베딩 벡터를 포함하는 조회 요청을 신경망 데이터베이스로 전달하여 질의에 대한 하나 이상의 검색 결과를 획득한다.
Absstract of: WO2024211290A1
The embodiments are directed to an inferential sensing system, methods and computer program product of an estimator for estimating parameters of complex nonlinear time-varying systems from scarce system output measurements. The estimator comprises a two-step process to accurately estimate the time-varying parameters of the time-varying system based on the input and output sample of the time-varying system. First, multiple filters in the high frequency processing loop, operating independently and concurrently process the input and output samples of the time-varying system to generate a hypersurface comprising time series objects. Each filter is restricted to adapt only a subset of the modeled time-varying parameters. The hypersurface comprising the time series objects is aggregated over several iterations of the high frequency processing loop. Second, the hypersurface is passed through a neural network in the low frequency processing loop to infer estimates of the time-varying system parameters.
Absstract of: AU2024219930A1
Documnt 1-20/09/2024 The present disclosure relates to systems and methods for detecting and detecting anomalies within a tree structure. In one implementation, the system may include 5 one or more memories storing instructions and one or more processors configured to execute the instructions. The instructions may include instructions to receive a new data structure related to an individual, convert the data structure into a Bayesian wavelet, using a tree structure of existing Bayesian wavelets, calculate one or more harmonics, determine a measure of whether the Bayesian wavelet 10 alters the one or more harmonics, and add the Bayesian wavelet to the tree structure when the measure is below a threshold. - 44-
Absstract of: US2024338414A1
This document relates to natural language processing using a framework such as a neural network. One example method involves obtaining a first document and a second document and propagating attention from the first document to the second document. The example method also involves producing contextualized semantic representations of individual words in the second document based at least on the propagating. The contextualized semantic representations can provide a basis for performing one or more natural language processing operations.
Absstract of: EP4443377A2
An apparatus to facilitate processing of a sparse matrix for arbitrary graph data is disclosed. The apparatus includes a graphics processing unit having a data management unit (DMU) that includes a scheduler for scheduling matrix operations, an active logic for tracking active input operands, and a skip logic for tracking unimportant input operands to be skipped by the scheduler. Processing circuitry is coupled to the DMU. The processing circuitry comprises a plurality of processing elements including logic to read operands and a multiplication unit to multiply two or more operands for the arbitrary graph data.
Absstract of: 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.
Absstract of: 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.
Nº publicación: US2024333925A1 03/10/2024
Applicant:
SK TELECOM CO LTD [KR]
SK TELECOM CO., LTD
Absstract of: 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.