公开(公告)号：US12131253B2

公开(公告)日：2024-10-29

申请号：US16609667

申请日：2018-05-01

申请人： NIPPON TELEGRAPH AND TELEPHONE CORPORATION

发明人： Takuhiro Kaneko ,  Kaoru Hiramatsu ,  Kunio Kashino

IPC分类号： G06N3/08 ,  G06N3/045 ,  G06N3/047 ,  G06N20/20 ,  G06T7/00 ,  G06T11/00

CPC分类号： G06N3/08 ,  G06N3/045 ,  G06N20/20 ,  G06T7/00 ,  G06T11/00 ,  G06N3/047

摘要： A signal generation device includes a variable generation unit and a signal generation unit. The variable generation unit generates a plurality of latent variables corresponding to a plurality of features of a signal. The signal generation unit inputs, to at least one neural network learned in advance, a latent variable representing attributes obtained by converting a part of the plurality of latent variables by an attribute vector representing attributes of a signal to be generated and the other part of the plurality of latent variables representing an identity and generates the signal to be generated using the at least one neural network.

公开(公告)号：US12131247B2

公开(公告)日：2024-10-29

申请号：US17126067

申请日：2020-12-18

申请人： WUHAN UNIVERSITY

发明人： Yigang He ,  Chaolong Zhang ,  Guolong Shi ,  Hui Zhang ,  Liulu He ,  Bolun Du

IPC分类号： G06N3/047 ,  G06F17/14 ,  G06N3/08

CPC分类号： G06N3/047 ,  G06F17/14 ,  G06N3/08

摘要： A transformer failure diagnosis method and system based on an integrated deep belief network are provided. The disclosure relates to the fields of electronic circuit engineering and computer vision. The method includes the following: obtaining a plurality of vibration signals of transformers of various types exhibiting different failure types, retrieving a feature of each of the vibration signals, and establishing training data through the retrieved features; training a plurality of deep belief networks exhibiting different learning rates through the training data and obtaining a failure diagnosis correct rate of each of the deep belief networks; and keeping target deep belief networks corresponding to the failure diagnosis correct rates that satisfy requirements, building an integrated deep belief network through each of the target deep belief networks, and performing a failure diagnosis on the transformers through the integrated deep belief network.

公开(公告)号：US20240354595A1

公开(公告)日：2024-10-24

申请号：US18136463

申请日：2023-04-19

申请人： Accenture Global Solutions Limited

发明人： Sumit PAI ,  Luca COSTABELLO

IPC分类号： G06N5/02 ,  G06N3/047

CPC分类号： G06N5/02 ,  G06N3/047

摘要： 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.

公开(公告)号：US12093148B2

公开(公告)日：2024-09-17

申请号：US17547972

申请日：2021-12-10

申请人： Shanghai Cambricon Information Technology Co., Ltd

发明人： Shaoli Liu ,  Xiaofu Meng ,  Xishan Zhang ,  Jiaming Guo ,  Di Huang ,  Yao Zhang ,  Yu Chen ,  Chang Liu

IPC分类号： G06F11/14 ,  G06N3/047 ,  G06N3/08

CPC分类号： G06F11/1476 ,  G06N3/047 ,  G06N3/08 ,  G06F2201/81 ,  G06F2201/865

摘要： The technical solution involves a board card including a storage component, an interface apparatus, a control component, and an artificial intelligence chip. The artificial intelligence chip is connected to the storage component, the control component, and the interface apparatus, respectively; the storage component is used to store data; the interface apparatus is used to implement data transfer between the artificial intelligence chip and an external device; and the control component is used to monitor a state of the artificial intelligence chip. The board card is used to perform an artificial intelligence operation.

公开(公告)号：US20240303472A1

公开(公告)日：2024-09-12

申请号：US18664948

申请日：2024-05-15

申请人： The Nielsen Company (US), LLC

发明人： Joshua Ivan Friedman ,  Tara Zeynep Baris ,  Neel Parekh

IPC分类号： G06N3/047 ,  G06N3/045 ,  G06N3/08 ,  G06Q30/0201 ,  G06Q30/0251 ,  H04N21/466

CPC分类号： G06N3/047 ,  G06N3/045 ,  G06N3/08 ,  G06Q30/0201 ,  G06Q30/0254 ,  H04N21/4663 ,  H04N21/4666

摘要： An example apparatus includes processor circuitry to: access first input data from meters, the meters to monitor media devices associated with a plurality of panelists, the first input data including media source data and panel data; reduce a dimensionality of the first input data to generate second input data of reduced dimensionality relative to the first input data, the dimensionality of the first input data to be reduced based on a prior probability of an audience rating associated with the plurality of panelists and an approximation of a dependency of the audience rating on at least one of the media source data and the panel data; and decode the second input data of reduced dimensionality to output a probability model parameter for a multivariate probability model, the multivariate probability model having dimensions corresponding to the first input data, the multivariate probability model to label census data.

公开(公告)号：US20240303471A1

公开(公告)日：2024-09-12

申请号：US18178684

申请日：2023-03-06

申请人： Intel Corporation

发明人： Raizy Kellerman ,  Alex Nayshtut ,  Omer Ben-Shalom

IPC分类号： G06N3/047

CPC分类号： G06N3/047

摘要： Implementations herein disclose an activation function for homomorphically-encrypted neural networks. A data-agnostic activation technique is provided that collects information about the distribution of the most-dominant activated locations in the feature maps of the trained model and maintains a map of those locations. This map, along with a defined percent of random locations, decides which neurons in the model are activated using an activation function. Advantages of implementations herein include allowing for efficient activation function computations in encrypted computations of neural networks, yet no data-dependent computation is done during inference time (e.g., data-agnostic). Implementations utilize negligible overhead in model storage, while preserving the same accuracy as with general activation functions and runs in orders of magnitude faster than approximation-based activation functions. Furthermore, implementations herein can be applied post-hoc to already-trained models and, as such, do not utilize fine-tuning.

公开(公告)号：US12079726B2

公开(公告)日：2024-09-03

申请号：US18107612

申请日：2023-02-09

申请人： Microsoft Technology Licensing, LLC

发明人： Nicolo Fusi ,  Francesco Paolo Casale ,  Jonathan Gordon

IPC分类号： G06N3/082 ,  G06F18/21 ,  G06F18/214 ,  G06N3/047 ,  G06N3/08

CPC分类号： G06N3/082 ,  G06F18/2148 ,  G06F18/217 ,  G06N3/047 ,  G06N3/08

摘要： Examples of the present disclosure describe systems and methods for probabilistic neural network architecture generation. In an example, an underlying distribution over neural network architectures based on various parameters is sampled using probabilistic modeling. Training data is evaluated in order to iteratively update the underlying distribution, thereby generating a probability distribution over the neural network architectures. The distribution is iteratively trained until the parameters associated with the neural network architecture converge. Once it is determined that the parameters have converged, the resulting probability distribution may be used to generate a resulting neural network architecture. As a result, intermediate architectures need not be fully trained, which dramatically reduces memory usage and/or processing time. Further, in some instances, it is possible to evaluate bigger architectures and/or larger batch sizes while also reducing neural network architecture generation time and maintaining or improving neural network accuracy.

公开(公告)号：US12073529B2

公开(公告)日：2024-08-27

申请号：US17526916

申请日：2021-11-15

申请人： International Business Machines Corporation

发明人： Sathya Santhar ,  Sarbajit K. Rakshit ,  Sridevi Kannan ,  Samuel Mathew Jawaharlal

IPC分类号： G06T19/20 ,  G06F18/214 ,  G06N3/044 ,  G06N3/045 ,  G06N3/047 ,  G06N3/08 ,  G06N3/084 ,  G06N3/088 ,  G06V10/82 ,  G06V40/20

CPC分类号： G06T19/20 ,  G06F18/2148 ,  G06N3/045 ,  G06N3/08 ,  G06N3/044 ,  G06N3/047 ,  G06N3/084 ,  G06N3/088 ,  G06T2219/2016 ,  G06V10/82 ,  G06V40/20

摘要： Provided is a system and method for moving a virtual object within virtual space in response to an external input supplied by a user. A machine learning model may predict a movement of the virtual object and implement such movement in a next frame of the virtual space. An example operation may include one or more of receiving a measurement of an external input of a user with respect to a virtual object displayed in virtual space, predicting, via execution of a machine learning model, a movement of the virtual object in the virtual space in response to the external input of the user based on the measurement of the external input of the user, and moving the virtual object in the virtual space based on the predicted movement of the virtual object by the machine learning model.

公开(公告)号：US12073321B2

公开(公告)日：2024-08-27

申请号：US17075618

申请日：2020-10-20

申请人： Tencent Technology (Shenzhen) Company Limited

发明人： Yang Feng ,  Lin Ma ,  Wei Liu ,  Jiebo Luo

IPC分类号： G06N3/08 ,  G06N3/045 ,  G06N3/047

CPC分类号： G06N3/08 ,  G06N3/045 ,  G06N3/047

摘要： Embodiments of this application disclose a method for training an image caption model, the image caption model including an encoding convolutional neural network (CNN) and a decoding recurrent neural network (RNN). The method includes: obtaining an image eigenvector of an image sample by using the encoding CNN; decoding the image eigenvector by using the decoding RNN, to obtain a sentence used for describing the image sample; determining a matching degree between the sentence obtained through decoding and the image sample and a smoothness degree of the sentence obtained through decoding, respectively; and adjusting the decoding RNN according to the matching degree and the smoothness degree.

公开(公告)号：US20240281643A1

公开(公告)日：2024-08-22

申请号：US18313907

申请日：2023-05-08

申请人： Microsoft Technology Licensing, LLC

发明人： Harsh SHRIVASTAVA ,  Urszula Stefania CHAJEWSKA

IPC分类号： G06N3/047

CPC分类号： G06N3/047

摘要： The present disclosure relates to recovering a sparse feature graph based on input data having a collection of samples and associated features. In particular, the systems described herein utilize a fully connected neural network to learn a regression of the input data and determine direct connections between features of the input data while the neural network satisfies one or more sparsity constraints. This regression may be used to recover a feature graph indicating direct connections between the features of the input data. In addition, the feature graph may be presented via an interactive presentation that enables a user to navigate nodes and edges of the graph to gain insights of the input data and associated features.