专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US11521044B2 Action detection by exploiting motion in receptive fields 有权
公开(公告)号：US11521044B2
公开(公告)日：2022-12-06
申请号：US15982181
申请日：2018-05-17
申请人： International Business Machines Corporation , The Board of Trustees of the University of Illinois
发明人： Khoi-Nguyen C. Mac , Raymond Alexander Yeh , Dhiraj Joshi , Minh N. Do , Rogerio Feris , Jinjun Xiong
IPC分类号： G06N3/04 , G06N3/08 , G06V40/20
摘要： Techniques regarding action detection based on motion in receptive fields of a neural network model are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a motion component that can extract a motion vector from a plurality of adaptive receptive fields in a deformable convolution layer of a neural network model. The computer executable components can also comprise an action detection component that can generate a spatio-temporal feature by concatenating the motion vector with a spatial feature extracted from the deformable convolution layer.

2. 发明授权

US11132512B2 Multi-perspective, multi-task neural network model for matching text to program code 有权
公开(公告)号：US11132512B2
公开(公告)日：2021-09-28
申请号：US16678341
申请日：2019-11-08
申请人： International Business Machines Corporation , The Board of Trustees of the University of Illinois
发明人： Lingfei Wu , Jinjun Xiong , Julia Constanze Hockenmaier , Rajarshi Haldar
IPC分类号： G06F40/30 , G06F16/2452 , G06N3/04 , G06N3/08
摘要： Embodiments of the invention describe a computer-implemented method that includes receiving a query that includes a query sequence having query characters grouped into query words. A segment of program code is retrieved from a database for evaluation. The program code includes a program code sequence including program code characters grouped into program code words. The query sequence, the query word, the program code sequence, and the program code word are each converted to sequence and word representations. Query sequence-level features, query word-level features, program code sequence-level features, and program code word-level features are extracted from the sequence and word representation. Similarity between the query and the segment of program code is determined by applying a similarity metric technique to the query sequence-level features, the query word-level features, the program code sequence-level features, and the program code word-level features.

3. 发明申请

US20220284277A1 NETWORK OF TENSOR TIME SERIES 有权
公开(公告)号：US20220284277A1
公开(公告)日：2022-09-08
申请号：US17184880
申请日：2021-02-25
申请人： International Business Machines Corporation , The Board of Trustees of the University of Illinois
发明人： Yada Zhu , Hanghang Tong , Baoyu Jing , Jinjun Xiong , Nitin Gaur , Anna Wanda Topol
IPC分类号： G06N3/08 , G06N3/04
摘要： One or more machine learning models for a network of tensor time series can be provided. Co-evolving time series having multiple modes can be received. A tensor graph convolutional network can be trained, using the co-evolving time series and adjacency matrices associated with the multiple modes in the co-evolving time series, to generate node embeddings associated with a snapshot of the co-evolving time series at time t. A tensor recurrent neural network can be trained to generate temporal dynamics associated with the co-evolving time series based on the generated node embeddings. A neural network model can be trained to forecast a prediction for the co-evolving time series based on the generated node embeddings and the generated temporal dynamics. The tensor graph convolutional network, the tensor recurrent neural network and the neural network model can be trained jointly.

4. 发明申请

US20220253426A1 EXPLAINING OUTLIERS IN TIME SERIES AND EVALUATING ANOMALY DETECTION METHODS 有权
公开(公告)号：US20220253426A1
公开(公告)日：2022-08-11
申请号：US17170164
申请日：2021-02-08
申请人： International Business Machines Corporation , The Board of Trustees of the University of Illinois
发明人： Yada Zhu , Jinjun Xiong , Jingrui He , Lecheng Zheng , Xiaodong Cui
IPC分类号： G06F16/23 , G06N3/04 , G06N3/08
摘要： Time series data can be received. A machine learning model can be trained using the time series data. A contaminating process can be estimated based on the time series data, the contaminating process including outliers associated with the time series data. A parameter associated with the contaminating process can be determined. Based on the trained machine learning model and the parameter associated with the contaminating process, a single-valued metric can be determined, which represents an impact of the contaminating process on the machine learning model's future prediction. A plurality of different outlier detecting machine learning models can be used to estimate the contaminating process and the single-valued metric can be determined for each of the plurality of different outlier detecting machine learning models. The plurality of different outlier detecting machine learning models can be ranked according to the associated single-valued metric.

5. 发明申请

US20210303803A1 TEXT STYLE TRANSFER USING REINFORCEMENT LEARNING 有权
公开(公告)号：US20210303803A1
公开(公告)日：2021-09-30
申请号：US16830106
申请日：2020-03-25
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION , The Board of Trustees of the University of Illinois
发明人： Lingfei Wu , Jinjun Xiong , Hongyu Gong , Suma Bhat , Wen-Mei Hwu
IPC分类号： G06F40/56 , G06N3/04 , G06F40/35 , G06F40/253
摘要： A computer-implemented method is provided for transferring a target text style using Reinforcement Learning (RL). The method includes pre-determining, by a Long Short-Term Memory (LSTM) Neural Network (NN), the target text style of a target-style natural language sentence. The method further includes transforming, by a hardware processor using the LSTM NN, a source-style natural language sentence into the target-style natural language sentence that maintains the target text style of the target-style natural language sentence. The method also includes calculating an accuracy rating of a transformation of the source-style natural language sentence into the target-style natural language sentence based upon rewards relating to at least the target text style of the source-style natural language sentence.

6. 发明申请

US20190354835A1 ACTION DETECTION BY EXPLOITING MOTION IN RECEPTIVE FIELDS 审中-公开
公开(公告)号：US20190354835A1
公开(公告)日：2019-11-21
申请号：US15982181
申请日：2018-05-17
申请人： International Business Machines Corporation , The Board of Trustees of the University of Illinois
发明人： Khoi-Nguyen C. Mac , Raymond Alexander Yeh , Dhiraj Joshi , Minh N. Do , Rogerio Feris , Jinjun Xiong
IPC分类号： G06N3/04 , G06N3/08 , G06K9/00
摘要： Techniques regarding action detection based on motion in receptive fields of a neural network model are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a motion component that can extract a motion vector from a plurality of adaptive receptive fields in a deformable convolution layer of a neural network model. The computer executable components can also comprise an action detection component that can generate a spatio-temporal feature by concatenating the motion vector with a spatial feature extracted from the deformable convolution layer.

7. 发明申请

US20220171923A1 Abstract Meaning Representation Parsing with Graph Translation 有权
公开(公告)号：US20220171923A1
公开(公告)日：2022-06-02
申请号：US17109008
申请日：2020-12-01
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION , THE BOARD OF TRUSTEES OF THE UNIVERSITY OF ILLINOIS
发明人： Lingfei Wu , Jinjun Xiong , Hongyu Gong , Suma Bhat , Wen-Mei Hwu
IPC分类号： G06F40/211 , G06N3/04 , G06N3/08 , G06K9/62 , G06N7/00
摘要： A computer-implemented method for generating an abstract meaning representation (“AMR”) of a sentence, comprising receiving, by a computing device, an input sentence and parsing the input sentence into one or more syntactic and/or semantic graphs. An input graph including a node set and an edge set is formed from the one or more syntactic and/or semantic graphs. Node representations are generated by natural language processing. The input graph is provided to a first neural network to provide an output graph having learned node representations aligned with the node representations in the input graph. The method further includes predicting via a second neural network, node label and predicting, via a third neural network, edge labels in the output graph. The AMR is generated based on the predicted node labels and predicted edge labels. A system and a non-transitory computer readable storage medium are also disclosed.

8. 发明授权

US11314950B2 Text style transfer using reinforcement learning 有权
公开(公告)号：US11314950B2
公开(公告)日：2022-04-26
申请号：US16830106
申请日：2020-03-25
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION , The Board of Trustees of the University of Illinois
发明人： Lingfei Wu , Jinjun Xiong , Hongyu Gong , Suma Bhat , Wen-Mei Hwu
IPC分类号： G06F40/56 , G06F40/253 , G06F40/35 , G06N3/04
摘要： A computer-implemented method is provided for transferring a target text style using Reinforcement Learning (RL). The method includes pre-determining, by a Long Short-Term Memory (LSTM) Neural Network (NN), the target text style of a target-style natural language sentence. The method further includes transforming, by a hardware processor using the LSTM NN, a source-style natural language sentence into the target-style natural language sentence that maintains the target text style of the target-style natural language sentence. The method also includes calculating an accuracy rating of a transformation of the source-style natural language sentence into the target-style natural language sentence based upon rewards relating to at least the target text style of the source-style natural language sentence.

9. 发明申请

US20210141863A1 MULTI-PERSPECTIVE, MULTI-TASK NEURAL NETWORK MODEL FOR MATCHING TEXT TO PROGRAM CODE 有权
公开(公告)号：US20210141863A1
公开(公告)日：2021-05-13
申请号：US16678341
申请日：2019-11-08
申请人： International Business Machines Corporation , The Board of Trustees of the University of Illinois
发明人： Lingfei Wu , Jinjun Xiong , Julia Constanze Hockenmaier , Rajarshi Haldar
IPC分类号： G06F17/27 , G06N3/08 , G06N3/04 , G06F16/2452
摘要： Embodiments of the invention describe a computer-implemented method that includes receiving a query that includes a query sequence having query characters grouped into query words. A segment of program code is retrieved from a database for evaluation. The program code includes a program code sequence including program code characters grouped into program code words. The query sequence, the query word, the program code sequence, and the program code word are each converted to sequence and word representations. Query sequence-level features, query word-level features, program code sequence-level features, and program code word-level features are extracted from the sequence and word representation. Similarity between the query and the segment of program code is determined by applying a similarity metric technique to the query sequence-level features, the query word-level features, the program code sequence-level features, and the program code word-level features.

10. 发明申请

US20170046307A1 RUNTIME OF CUBLAS MATRIX MULTIPLICATION ON GPU 有权
标题翻译： GPU上的CUBLAS矩阵多项式运行
公开(公告)号：US20170046307A1
公开(公告)日：2017-02-16
申请号：US14823889
申请日：2015-08-11
申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION
发明人： Alexey Y. Lvov , Jinjun Xiong , Vladimir Zolotov
IPC分类号： G06F17/16 , G06T1/20
CPC分类号： G06F17/16 , G06T1/20 , G06T2200/28
摘要： Methods for improving matrix multiplication runtimes are provided. A method includes determining, by a GPU, optimal partitions for matrix-by-matrix multiplication of two factor matrices having sizes known a priori. The determining step includes performing offline a plurality of matrix-by-matrix multiplication executions, each for a respective different combination of two-way partitions across a plurality of partition sizes. The determining step further includes determining offline a respective performance number for each of the executions based on runtime. The determining step also includes recursively repeating offline said performing and determining steps until the respective performance number ceases to improve for best-performing combinations of the two-way partitions and saving the best performing combinations of the two-way partitions as the optimal partitions. The method further includes performing online, by the GPU, the matrix-by-matrix multiplication of the two factor matrices using calls for a given one of the best performing combinations of the two-way partitions.
摘要翻译：提供了改进矩阵乘法运行时的方法。一种方法包括由GPU确定具有先验已知的尺寸的两个因子矩阵的逐矩阵乘法的最佳分区。所述确定步骤包括执行多个矩阵逐矩阵乘法执行，所述多个逐行矩阵乘法执行各自针对跨多个分区大小的双向分区的相应不同组合。所述确定步骤还包括基于运行时确定每个所述执行的脱机相应的性能编号。确定步骤还包括递归地重复离线所述执行和确定步骤，直到相应的性能编号不再改进以用于双向分区的最佳执行组合并且将双向分区的最佳执行组合保存为最佳分区。该方法还包括使用对双向分区的最佳执行组合中的给定的一个的调用，由GPU在线执行两个因子矩阵的逐矩阵乘法。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式