-
公开(公告)号：US20230075600A1
公开(公告)日：2023-03-09
申请号：US17468028
申请日：2021-09-07
发明人： Yiming Ma , Lili Zhang , Wei Kang , Jaewon Yang
摘要： Techniques for training and using a neural network to make predictions using trajectory modelling are disclosed herein. In some embodiments, a computer-implemented method comprises: training a first neural network with a first machine learning algorithm using training data, the first neural network being a recurrent neural network, the training data including a plurality of reference career trajectories, each reference career trajectory in the plurality of reference career trajectories comprising a sequence of reference career segments, each reference career segment in the sequence of reference career segments comprising reference profile data and reference time data indicating a position of the reference career segment within the sequence of reference career segments, the training data also including a corresponding set of reference skills for each reference career segment.
-
公开(公告)号：US20200311613A1
公开(公告)日：2020-10-01
申请号：US16370156
申请日：2019-03-29
发明人： Yiming Ma , Jun Jia , Yi Wu , Xuhong Zhang , Leon Gao , Baolei Li , Bee-Chung Chen , Bo Long
摘要： Herein are techniques for configuring, integrating, and operating trainable tensor transformers that each encapsulate an ensemble of trainable machine learning (ML) models. In an embodiment, a computer-implemented trainable tensor transformer uses underlying ML models and additional mechanisms to assemble and convert data tensors as needed to generate output records based on input records and inferencing. The transformer processes each input record as follows. Input tensors of the input record are converted into converted tensors. Each converted tensor represents a respective feature of many features that are capable of being processed by the underlying trainable models. The trainable models are applied to respective subsets of converted tensors to generate an inference for the input record. The inference is converted into a prediction tensor. The prediction tensor and input tensors are stored as output tensors of a respective output record for the input record.
-
公开(公告)号：US20190122030A1
公开(公告)日：2019-04-25
申请号：US15793861
申请日：2017-10-25
发明人： Florian Raudies , Yi Zhen , Ajith Muralidharan , Yiming Ma
CPC分类号： G06K9/00288 , G06K9/00261 , G06K9/00281 , G06T11/60 , H04L67/306 , H04N7/155
摘要： Disclosed are systems, methods, and non-transitory computer-readable media for automated profile image generation based on scheduled video conferences. A profile image generation system generates, based on image data captured during a first video conference, a first facial feature data set for a first identified face identified from the image data. The first facial feature data set includes numeric values representing the first identified face. The profile image generation system calculates, based on the first facial feature data set and historic facial feature data sets generated from image data captured during previous video conferences, a first value indicating a likelihood that the first identified face is a first meeting participant that participated in the first video conference. The profile image generation system determines that the first value meets or exceeds a threshold value, and in response, determines that the first identified face is the first meeting participant.
-
公开(公告)号：US11704566B2
公开(公告)日：2023-07-18
申请号：US16446924
申请日：2019-06-20
发明人： Yiming Ma , Menglin L. Brown , Bee-Chung Chen , Sheng Wu , Jun Jia , Bo Long
IPC分类号： G06N3/00 , G06N3/082 , G06N20/20 , G06F11/34 , G06F18/214
CPC分类号： G06N3/082 , G06F11/3495 , G06F18/214 , G06N20/20
摘要： The disclosed embodiments provide a system for processing data. During operation, the system obtains a training dataset containing a first set of records associated with a first set of identifier (ID) values and an evaluation dataset containing a second set of records associated with a second set of ID values. Next, the system selects a random subset of ID values from the second set of ID values. The system then generates a sampled evaluation dataset comprising a first subset of records associated with the random subset of ID values in the second set of records. The system also generates a sampled training dataset comprising a second subset of records associated with the random subset of ID values in the first set of records. Finally, the system outputs the sampled training dataset and the sampled evaluation dataset for use in training and evaluating a machine learning model.
-
公开(公告)号：US20190197013A1
公开(公告)日：2019-06-27
申请号：US15879316
申请日：2018-01-24
发明人： Bee-Chung Chen , Deepak Agarwal , Alex Shelkovnykov , Josh Fleming , Yiming Ma
CPC分类号： G06N20/00 , G06F16/903 , G06K9/6256 , G06K9/6286 , G06K9/6287 , G06N7/005 , G06Q10/063112 , G06Q10/1053 , G06Q50/01
摘要： Iterations of a machine learned model training process are performed until a convergence occurs. A fixed effects machine learned model is trained using a first machine learning algorithm. Residuals of the training of the fixed effects machine learned model are determined by comparing results of the trained fixed effects machine learned model to a first set of target results. A first random effects machine learned model is trained using a second machine learning algorithm and the residuals of the training of the fixed effects machine learned model. Residuals of the training of the first random effect machine learned model are determined by comparing results of the trained first random effects machine learned model to a second set of target result, in each subsequent iteration the training of the fixed effects machine learned model uses residuals of the training of a last machine learned model trained in a previous iteration.
-
公开(公告)号：US11768874B2
公开(公告)日：2023-09-26
申请号：US16225888
申请日：2018-12-19
发明人： Yiming Ma , Xuhong Zhang , Wei Lu , Mingzhou Zhou
IPC分类号： G06F16/901 , G06F16/906 , G06N20/00
CPC分类号： G06F16/9017 , G06F16/906 , G06F16/9014 , G06N20/00
摘要： The disclosed embodiments provide a system for processing data. During operation, the system applies a first set of hash functions to a first entity identifier (ID) for a first entity to generate a first set of hash values. Next, the system produces a first set of intermediate vectors from the first set of hash values and a first set of lookup tables by matching each hash value in the first set of hash values to an entry in a corresponding lookup table in the first set of lookup tables. The system then performs an element-wise aggregation of the first set of intermediate vectors to produce a first embedding. Finally, the system outputs the first embedding for use by a machine learning model.
-
公开(公告)号：US11106982B2
公开(公告)日：2021-08-31
申请号：US16109411
申请日：2018-08-22
发明人： Yiming Ma , Alex Shelkovnykov , Josh Fleming , Bee-Chung Chen , Bo Long
摘要： In an example embodiment, a warm-start training solution is used to dramatically reduce the computational resources needed to train when retraining a generalized additive mixed-effect (GAME) model. The problem of retraining time is particularly applicable to GAME models, since these models take much longer to train as the data grows. In the past, the strategy to reduce computational resources during retraining was to use less training data, but this affects the model quality, especially for GAME models, which rely on fine-grained sub-models at, for example, member or item levels. The present solution addresses the computational resources issues without sacrificing GAME model accuracy.
-
公开(公告)号：US20200065678A1
公开(公告)日：2020-02-27
申请号：US16109411
申请日：2018-08-22
发明人： Yiming Ma , Alex Shelkovnykov , Josh Fleming , Bee-Chung Chen , Bo Long
摘要： In an example embodiment, a warm-start training solution is used to dramatically reduce the computational resources needed to train when retraining a generalized additive mixed-effect (GAME) model. The problem of retraining time is particularly applicable to GAME models, since these models take much longer to train as the data grows. In the past, the strategy to reduce computational resources during retraining was to use less training data, but this affects the model quality, especially for GAME models, which rely on fine-grained sub-models at, for example, member or item levels. The present solution addresses the computational resources issues without sacrificing GAME model accuracy.
-
公开(公告)号：US20190332569A1
公开(公告)日：2019-10-31
申请号：US15964586
申请日：2018-04-27
发明人： Yiming Ma , Wei Lu , Jun Jia , Bee-Chung Chen , Bo Long
摘要： In an example embodiment, knowledge discovery using deep learning is combined with the scalability and personalization capabilities of generalized additive mixed effect (GAME) modeling. Specifically, features learned in a last fully connected layer of a deep learning model may be used to augment features used in a fixed or random effects training portion of a GAME model.
-
公开(公告)号：US10423821B2
公开(公告)日：2019-09-24
申请号：US15793861
申请日：2017-10-25
发明人： Florian Raudies , Yi Zhen , Ajith Muralidharan , Yiming Ma
摘要： Disclosed are systems, methods, and non-transitory computer-readable media for automated profile image generation based on scheduled video conferences. A profile image generation system generates, based on image data captured during a first video conference, a first facial feature data set for a first identified face identified from the image data. The first facial feature data set includes numeric values representing the first identified face. The profile image generation system calculates, based on the first facial feature data set and historic facial feature data sets generated from image data captured during previous video conferences, a first value indicating a likelihood that the first identified face is a first meeting participant that participated in the first video conference. The profile image generation system determines that the first value meets or exceeds a threshold value, and in response, determines that the first identified face is the first meeting participant.
-
-
-
-
-
-
-
-
-
搜索结果
12 条记录 (耗时 0.022 秒)
