公开(公告)号：US20230351158A1

公开(公告)日：2023-11-02

申请号：US18138945

申请日：2023-04-25

Applicant: Siemens Aktiengesellschaft

Inventor： Melanie Kienberger ,  Johannes Stübinger ,  Ali Al Hage Ali ,  Aleksandra Thamm ,  Dominik Zacharias ,  Benjamin Amschler ,  Florian Thamm

IPC: G06N3/0455 ,  G06F17/14 ,  G06N3/088 ,  H02J13/00

CPC classification number: G06N3/0455 ,  G06F17/142 ,  G06N3/088 ,  H02J13/00002

Abstract: An apparatus, system and method for detecting anomalies in a grid are disclosed. The method includes transforming data acquired from the grid based on at least one of a Fast Fourier Transformation and a spectrogram of the data, wherein the data acquired includes data associated with at least one of grid voltage, grid current, grid frequency, phase; fitting the data using a fitting function initialized using at least the transformed data, wherein the fitting function includes at least one of a sinusoidal function; or generating a lower representation of at least one of the data acquired and the transformed data; and detecting the anomaly in the grid based on at least one outlier detected in the fitted data or the lower representation of data using at least one of a parameter deviation and the similarity index.

公开(公告)号：US11804998B2

公开(公告)日：2023-10-31

申请号：US17154215

申请日：2021-01-21

Applicant: QUALCOMM Incorporated

Inventor： June Namgoong ,  Krishna Kiran Mukkavilli ,  Taesang Yoo ,  Naga Bhushan ,  Tingfang Ji ,  Pavan Kumar Vitthaladevuni ,  Jay Kumar Sundararajan

IPC: H04L27/26 ,  H04B3/23 ,  H04B3/06 ,  G06N3/08 ,  H04B3/46 ,  G06N3/088 ,  H04L5/00 ,  H04W72/04 ,  G06F18/214 ,  G06N3/045

CPC classification number: H04L27/2618 ,  G06F18/2148 ,  G06N3/045 ,  G06N3/08 ,  G06N3/088 ,  H04B3/06 ,  H04B3/238 ,  H04B3/46 ,  H04L5/0048 ,  H04L27/2615 ,  H04W72/04

Abstract: Various embodiments include methods performed in receiver circuitry of a wireless communication device for demodulating wireless transmission waveforms to reconstruct data tones, which may include receiving, from a transmitter, wireless transmission waveforms that includes peak reduction tones (PRTs) that were inserted by a PRT neural network in the transmitter, and demodulating the received wireless transmission waveforms using a decoder neural network that has been trained based on outputs of the transmitter to output a reconstruction of the data tones. Further embodiments include exchanging information between the transmitter and receiver circuitry to coordinate the PRT neural network used for inserting PRTs in the transmitting wireless communication device and the decoder neural network used in the receiving wireless communication device for demodulating transmission waveforms received from the transmitting wireless communication device.

公开(公告)号：US11803939B2

公开(公告)日：2023-10-31

申请号：US17242473

申请日：2021-04-28

Applicant: Shanghai United Imaging Intelligence Co., LTD.

Inventor： Yikang Liu ,  Zhang Chen ,  Xiao Chen ,  Shanhui Sun ,  Terrence Chen

IPC: G06T19/20 ,  G06T3/40 ,  G16H30/20 ,  G16H30/40 ,  G06T11/00 ,  G06N3/088

CPC classification number: G06T3/4053 ,  G06N3/088 ,  G06T3/4046 ,  G06T11/006 ,  G16H30/40

Abstract: An unsupervised machine learning method with self-supervision losses improves a slice-wise spatial resolution of 3D medical images with thick slices, and does not require high resolution images as the ground truth for training. The method utilizes information from high-resolution dimensions to increase a resolution of another desired dimension.

公开(公告)号：US20230342287A1

公开(公告)日：2023-10-26

申请号：US18211407

申请日：2023-06-19

Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC.

Inventor： COLIN BRUCE CLEMENT ,  SHAO KUN DENG ,  NEELAKANTAN SUNDARESAN ,  ALEXEY SVYATKOVSKIY ,  MICHELE TUFANO

IPC: G06F11/36 ,  G06F8/41 ,  G06F8/77 ,  G06N3/04 ,  G06N3/088

CPC classification number: G06F11/3684 ,  G06F8/41 ,  G06F8/77 ,  G06N3/04 ,  G06N3/088

Abstract: A test-driven development system utilizes a neural transformer model with attention to generate method bodies for a focal method given its associated test cases, and optionally a method signature and a docstring of the focal method. The candidate method bodies are validated for syntactic correctness, tested using the given test cases, and tested with a donor class in a target system. Those candidate method bodies passing the validation and testing are then ranked based on a PLUM score that analyzes the candidate method bodies against various quality and performance metrics.

公开(公告)号：US11797862B2

公开(公告)日：2023-10-24

申请号：US16749570

申请日：2020-01-22

Applicant: Google LLC

Inventor： Yang Song ,  Raghav Gupta ,  Dengyong Zhou ,  Sanqiang Zhao

IPC: G06N3/088 ,  G06F40/284 ,  G06N3/045

CPC classification number: G06N3/088 ,  G06F40/284 ,  G06N3/045

Abstract: Provided is a knowledge distillation technique for training a student language model that, relative to a larger teacher language model, has a significantly smaller vocabulary, lower embedding dimensions, and/or hidden state dimensions. Specifically, aspects of the present disclosure are directed to a dual-training mechanism that trains the teacher and student language models simultaneously to obtain optimal word embeddings for the student vocabulary. In some implementations, this approach can be combined with learning shared projection matrices that transfer layer-wise knowledge from the teacher language model to the student language model. Example experimental results have also demonstrated higher compression efficiency and accuracy when compared with other state-of-the-art compression techniques, including the ability to compress the BERTBASE model by more than 60×, with only a minor drop in downstream task metrics, resulting in a language model with a footprint of under 7 MB.

公开(公告)号：US11797591B2

公开(公告)日：2023-10-24

申请号：US17193748

申请日：2021-03-05

Applicant: NAVER CORPORATION

Inventor： Matthias Galle ,  Maximin Coavoux ,  Hady Elsahar

IPC: G06F16/30 ,  G06F16/34 ,  G06F16/35 ,  G06N3/088

CPC classification number: G06F16/345 ,  G06F16/35 ,  G06N3/088

Abstract: A method for generating enriched training data for a multi-source transformer neural network for generation of a summary of one or more passages of input text comprises creating, from a plurality of input text sets, training points each comprising an input text subset of the input text set and a corresponding reference input text from the input text set, wherein the size of the input text subset is a predetermined number. Control codes are selected based on reference features corresponding to categorical labels of reference texts in the created training points. The input text is enriched with the selected control codes to generate enriched training data.

公开(公告)号：US11797514B2

公开(公告)日：2023-10-24

申请号：US17934001

申请日：2022-09-21

Applicant: NASDAQ, INC.

Inventor： Xuyang Lin ,  Tudor Morosan ,  Douglas Hamilton ,  Shihui Chen ,  Hyunsoo Jeong ,  Jonathan Rivers ,  Leonid Rosenfeld

IPC: G06F16/00 ,  G06F16/23 ,  G06N3/088 ,  G06F18/214 ,  G06N3/045

CPC classification number: G06F16/2358 ,  G06F18/2155 ,  G06N3/045 ,  G06N3/088

Abstract: A computer system is provided for monitoring and detecting changes in a data generating processes, which may be under a multi-dimensional and unsupervised setting. A target dataset is split into paired subgroups by a separator and one or more detectors are applied to detect changes, anomalies, inconsistencies, and the like between the paired subgroups. Metrics may be generated by the detector(s), which are then passed to an evaluating system.

公开(公告)号：US20230334295A1

公开(公告)日：2023-10-19

申请号：US18133755

申请日：2023-04-12

Applicant: Raytheon Company

Inventor： Joshua A. Binkley ,  Christine R. Nezda ,  Marta Tatu

IPC: G06N3/0455 ,  G06N3/088 ,  G06F18/2321

CPC classification number: G06N3/0455 ,  G06N3/088 ,  G06F18/2321

Abstract: Discussed herein are devices, systems, and methods for unsupervised pattern discovery using continuous-time dynamic graphs. A method can include receiving, from a graph neural network (GNN), source node embeddings and destination node embeddings, clustering the destination node embeddings generated by the GNN resulting in first groups of destination node embeddings, removing, from the destination node embeddings, embeddings from a noise group of the first groups resulting in signal destination node embeddings, clustering the signal destination node embeddings resulting in second groups of destination node embeddings, and identifying a pattern in the destination node embeddings and source node embeddings based on the second groups of destination node embeddings, the source node embeddings, and the destination node embeddings.

公开(公告)号：US11790044B2

公开(公告)日：2023-10-17

申请号：US17847408

申请日：2022-06-23

Applicant: Silicon Laboratories Inc.

Inventor： Javier Elenes ,  Antonio Torrini

IPC: G06F18/21 ,  G06N3/088 ,  G06F18/25 ,  G06F18/20 ,  G06F18/214

CPC classification number: G06F18/2193 ,  G06F18/2148 ,  G06F18/251 ,  G06F18/285 ,  G06N3/088

Abstract: In an embodiment, an apparatus includes: a sensor to sense real world information; a digitizer coupled to the sensor to digitize the real world information into digitized information; a signal processor coupled to the digitizer to process the digitized information into an image; a discriminator coupled to the signal processor to determine, based at least in part on the image, whether the real world information comprises an anomaly, where the discriminator is trained via a generative adversarial network; and a controller coupled to the discriminator.

公开(公告)号：US11783191B2

公开(公告)日：2023-10-10

申请号：US17499320

申请日：2021-10-12

Applicant: Samsung Electronics Co., Ltd.

Inventor： Yusun Lim

IPC: G06N3/08 ,  G06N3/084 ,  G06F18/22 ,  G06F18/25 ,  G06N3/044 ,  G06N3/04 ,  G06N3/088

CPC classification number: G06N3/084 ,  G06F18/22 ,  G06F18/256 ,  G06N3/044 ,  G06N3/08 ,  G06N3/04 ,  G06N3/088

Abstract: An artificial intelligence (AI) system for simulating functions such as recognition, determination, and so forth of human brains by using a mechanical learning algorithm like deep learning, or the like, and an application thereof is provided. A method of providing a text-related image is provided. The method includes obtaining a text, determining at least one image related to the obtained text based on a degree of relatedness between a result of applying a first AI data recognition model to the obtained text and a result of applying a second AI data recognition model to a user-accessible image, and displaying the determined at least one image to a user.