-
公开(公告)号：US20240211724A1
公开(公告)日：2024-06-27
申请号：US18556619
申请日：2021-08-11
发明人： Haofeng KOU , Xing LI , Huimeng ZHENG , Lei WANG , Zhen CHEN
IPC分类号： G06N3/04
CPC分类号： G06N3/04
摘要： Modern deep neural network (DNN) models have many layers with a single layer potentially involving large matrix multiplications. Such heavy calculation brings challenges to deploy such DNN models on a single edge device, which has relatively limited computation resources. Therefore, multiple and even heterogeneous edge devices may be required for applications with stringent latency requirements. Disclosed in the present patent documents are embodiments of a model scheduling framework that schedules multiple models on a heterogeneous platform. Multiple-model heterogeneous computing is partitioned into a neural computation optimizer (NCO) part and a neural computation accelerator (NCA) part. The migration, transition, or transformation of DNN models from cloud to edge is handled by the NCO, while the deployment of the transformed DNN models on the heterogeneous platform is handled by the NCA. Such a separation of implementation simplifies task execution and improves the flexibility for the overall framework.
-
2.发明授权公开(公告)号：US12014398B2
公开(公告)日：2024-06-18
申请号：US18250525
申请日：2021-07-07
发明人： Hongliang Fei , Jingyuan Zhang , Xingxuan Zhou , Junhao Zhao , Banghu Yin , Ping Li
IPC分类号： G06Q30/0251 , G06Q30/0201
CPC分类号： G06Q30/0269 , G06Q30/0201
摘要： Deep neural network (DNN) models have been widely used for user-relevance content prediction. Presented herein are embodiments of a new user-relevance framework, which may be referred as Gating-Enhanced Multi-task Neural Networks (GemNN) embodiments. Neural network-based multi-task learning model embodiments herein predict user engagement with content in a coarse-to-fine manner, which gradually reduces content candidates and allows parameter sharing from upstream tasks to downstream tasks to improve the training efficiency. Also, in one or more embodiments, a gating mechanism was introduced between embedding layers and multi-layer perceptions to learn feature interactions and control the information flow fed to MLP layers. Tested embodiments demonstrated considerable improvements over prior approaches.
-
公开(公告)号：US11922287B2
公开(公告)日：2024-03-05
申请号：US17040039
申请日：2020-07-15
发明人： Dingcheng Li , Xu Li , Jun Wang , Ping Li
CPC分类号： G06N3/042 , G06N3/08 , H04N21/251
摘要： Described herein are embodiments of a reinforcement learning based large-scale multi-objective ranking system. Embodiments of the system may be used for optimizing short-video recommendation on a video sharing platform. Multiple competing ranking objective and implicit selection bias in user feedback are the main challenges in real-world platform. In order to address those challenges, multi-gate mixture of experts (MMoE) and soft actor critic (SAC) are integrated together into a MMoE_SAC system. Experiment results demonstrate that embodiments of the MMoE_SAC system may greatly reduce a loss function compared to systems only based on single strategies.
-
公开(公告)号：US11788845B2
公开(公告)日：2023-10-17
申请号：US16770614
申请日：2018-06-29
发明人： Mingyu Chen , Yingze Bao , Xin Zhou , Haomin Liu
CPC分类号： G01C21/30 , G05D1/0088
摘要： Described herein are systems and methods that improve the success rate of relocalization and eliminate the ambiguity of false relocalization by exploiting motions of the sensor system. In one or more embodiments, during a relocalization process, a snapshot is taken using one or more visual sensors and a single-shot relocalization in a visual map is implemented to establish candidate hypotheses. In one or more embodiments, the sensors move in the environment, with a movement trajectory tracked, to capture visual representations of the environment in one or more new poses. As the visual sensors move, the relocalization system tracks various estimated localization hypotheses and removes false ones until one winning hypothesis. Once the process is finished, the relocalization system outputs a localization result with respect to the visual map.
-
公开(公告)号：US20230229119A1
公开(公告)日：2023-07-20
申请号：US18009976
申请日：2021-02-10
发明人： Huimeng ZHENG , Haofeng KOU
CPC分类号： G05B13/0265 , G06N20/00
摘要： One application of deep learning methods and labelled data is for industrial production or work applications. For such applications implemented with machine learning applications, massive amounts of data are required to train, validate, and/or tune models for better fitting the requirements. However, obtaining such data has typically be costly and difficult. Embodiments provide adaptable processes that provide data labelling methods for work settings. Embodiments take advantage of the work or production processes to label and collect data, which save time and money and improves accuracy. Embodiments prevent or reduce the need for worker training costs and human mistake-triggered data labelling problems. Embodiments also improve data labelling quality and speed-up of the development cycle.
-
公开(公告)号：US11687711B2
公开(公告)日：2023-06-27
申请号：US16703718
申请日：2019-12-04
发明人： Hao Tian , Xi Chen , Jeff ChienYu Wang , Daming Lu
IPC分类号： G06F40/216 , G06F40/30 , G10L13/00 , G06V20/40 , G06V10/762 , G06V10/764 , G06V10/82 , G06F18/2321
CPC分类号： G06F40/216 , G06F40/30 , G06V10/763 , G06V10/764 , G06V10/82 , G06V20/43 , G10L13/00 , G06F18/2321
摘要： Embodiments of the present disclosure provide a method and apparatus for generating a commentary. The method may include: acquiring at least one news cluster composed of pieces of news generated within a first preset time length, the pieces of news in the news cluster direct to a given news event; determining a target news cluster based on the at least one news cluster; determining, for each piece of news in the target news cluster, a score of being suitable for generating a commentary for the piece of news; and generating, based on a piece of target news, a commentary for the target news cluster, where the piece of target news is a piece of news having a highest score of being suitable for generating a commentary in the target news cluster.
-
公开(公告)号：US11653459B2
公开(公告)日：2023-05-16
申请号：US17479639
申请日：2021-09-20
发明人： Tianyi Gao
CPC分类号： H05K5/0221 , H05K7/1488 , H05K7/20763
摘要： A server includes a chassis; a base panel fixedly coupled to the chassis; a movable panel coupled to the base panel; and a locking member fixedly coupled to the movable panel. The movable panel is movable relative to the base panel in a moving direction between an unlocked position where the locking member is configured to be disengaged with a locking panel of an electronic rack, and a locked position where the locking member is configured to be engaged with the locking panel of the electronic rack.
-
公开(公告)号：US11511760B2
公开(公告)日：2022-11-29
申请号：US16643154
申请日：2020-01-23
发明人： Yu Wang , Qi Luo , Yu Cao , Zongbao Feng , Longtao Lin , Xiangquan Xiao , Jinghao Miao , Jiangtao Hu , Jingao Wang , Shu Jiang , Jinyun Zhou , Jiaxuan Xu
IPC分类号： B60W40/105 , G06F16/23 , G06F16/9035 , B60W50/00
摘要： Systems and methods are disclosed for collecting driving data from simulated autonomous driving vehicle (ADV) driving sessions and real-world ADV driving sessions. The driving data is processed to exclude manual (human) driving data and to exclude data corresponding to the ADV being stationary (not driving). Data can further be filtered based on driving direction: forward or reverse driving. Driving data records are time stamped. The driving data can be aligned according to the timestamp, then a standardized set of metrics is generated from the collected, filtered, and time-aligned data. The standardized set of metrics are used to grade the performance the control system of the ADV, and to generate an updated ADV controller, based on the standardized set of metrics.
-
公开(公告)号：US11488389B2
公开(公告)日：2022-11-01
申请号：US16494738
申请日：2019-08-30
发明人： Shuai Wang , Manjiang Zhang , Yaoming Shen , Xiangfei Zhou , Lingchang Li , Xianfei Li
摘要： In some implementations, a method of verifying operation of a sensor is provided. The method includes causing a sensor to obtain sensor data at a first time, wherein the sensor obtains the sensor data by emitting waves towards a detector. The method also includes determining that the detector has detected the waves at a second time. The method further includes receiving the sensor data from the sensor at a third time. The method further includes verifying operation of the sensor based on at least one of the first time, the second time, or the third time.
-
公开(公告)号：US20220315046A1
公开(公告)日：2022-10-06
申请号：US16627257
申请日：2019-12-20
发明人： Shu JIANG , Qi LUO , Jinghao MIAO , Jiangtao HU , Yu WANG , Jiaxuan XU , Jinyun ZHOU , Kuang HU , Chao MA
摘要： In one embodiment, simulation of an autonomous driving vehicle (ADV) includes capturing first data that includes a control command output by an autonomous vehicle controller of the ADV, and capturing second data that includes the control command being implemented at a control unit of the ADV. The control command, for example, a steering command, a braking command, or a throttle command, is implemented by the ADV to affect movement of the ADV. A latency model is determined based on comparing the first data with the second data, where the latency model defines time delay and/or amplitude difference between the first data and the second data. The latency model is applied in a virtual driving environment.
-
-
-
-
-
-
-
-
-
搜索结果
212 条记录 (耗时 0.031 秒)
