-
公开(公告)号：US11544620B2
公开(公告)日：2023-01-03
申请号：US16253366
申请日：2019-01-22
发明人： Kin Gwn Lore , Kishore K. Reddy
摘要： According to an embodiment of the present disclosure, a method of training a machine learning model is provided. Input data is received from at least one remote device. A classifier is evaluated by determining a classification accuracy of the input data. A training data matrix of the input data is applied to a selected context autoencoder of a knowledge bank of autoencoders including at least one context autoencoder and the training data matrix is determined to be out of context for the selected autoencoder. The training data matrix is applied to each other context autoencoder of the at least one autoencoder and the training data matrix is determined to be out of context for each other context autoencoder. A new context autoencoder is constructed.
-
公开(公告)号：US11422546B2
公开(公告)日：2022-08-23
申请号：US15536713
申请日：2015-12-18
摘要： A method includes fusing multi-modal sensor data from a plurality of sensors having different modalities. At least one region of interest is detected in the multi-modal sensor data. One or more patches of interest are detected in the multi-modal sensor data based on detecting the at least one region of interest. A model that uses a deep convolutional neural network is applied to the one or more patches of interest. Post-processing of a result of applying the model is performed to produce a post-processing result for the one or more patches of interest. A perception indication of the post-processing result is output.
-
公开(公告)号：US11062207B2
公开(公告)日：2021-07-13
申请号：US15797035
申请日：2017-10-30
摘要： Data indicative of a plurality of observations of an environment are received at a control system. Machine learning using deep reinforcement learning is applied to determine an action based on the observations. The deep reinforcement learning applies a convolutional neural network or a deep auto encoder to the observations and applies a training set to locate one or more regions having a higher reward. The action is applied to the environment. A reward token indicative of alignment between the action and a desired result is received. A policy parameter of the control system is updated based on the reward token. The updated policy parameter is applied to determine a subsequent action responsive to a subsequent observation.
-
4.发明授权公开(公告)号：US10733721B2
公开(公告)日：2020-08-04
申请号：US16549332
申请日：2019-08-23
摘要： A material characterization system includes an imaging unit, a material characterization controller, and an imaging unit controller. The electronic imaging unit generates a test image of a specimen composed of a material. The electronic material characterization controller determines values of a plurality of parameters and maps the parameters to corresponding ground truth labeled outputs. The mapped parameters are applied to at least one test image to predict a presence of at least one target attribute of the specimen in response to applying the learned parameters. The test image is convert to a selected output image format so as to generate a synthetic image including the predicted at least one attribute. The electronic imaging unit controller performs a material characterization analysis that characterizes the material of the specimen based on the predicted at least one attribute included in the synthetic image.
-
公开(公告)号：US20200234179A1
公开(公告)日：2020-07-23
申请号：US16253366
申请日：2019-01-22
发明人： Kin Gwn Lore , Kishore K. Reddy
摘要： According to an embodiment of the present disclosure, a method of training a machine learning model is provided. Input data is received from at least one remote device. A classifier is evaluated by determining a classification accuracy of the input data. A training data matrix of the input data is applied to a selected context autoencoder of a knowledge bank of autoencoders including at least one context autoencoder and the training data matrix is determined to be out of context for the selected autoencoder. The training data matrix is applied to each other context autoencoder of the at least one autoencoder and the training data matrix is determined to be out of context for each other context autoencoder. A new context autoencoder is constructed.
-
6.发明申请公开(公告)号：US20190378267A1
公开(公告)日：2019-12-12
申请号：US16549332
申请日：2019-08-23
摘要： A material characterization system includes an imaging unit, a material characterization controller, and an imaging unit controller. The electronic imaging unit generates a test image of a specimen composed of a material. The electronic material characterization controller determines values of a plurality of parameters and maps the parameters to corresponding ground truth labeled outputs. The mapped parameters are applied to at least one test image to predict a presence of at least one target attribute of the specimen in response to applying the learned parameters. The test image is convert to a selected output image format so as to generate a synthetic image including the predicted at least one attribute. The electronic imaging unit controller performs a material characterization analysis that characterizes the material of the specimen based on the predicted at least one attribute included in the synthetic image.
-
7.发明授权公开(公告)号：US10430937B2
公开(公告)日：2019-10-01
申请号：US15714339
申请日：2017-09-25
摘要： A material characterization system includes an imaging unit, a material characterization controller, and an imaging unit controller. The electronic imaging unit generates a test image of a specimen composed of a material. The electronic material characterization controller determines values of a plurality of parameters and maps the parameters to corresponding ground truth labeled outputs. The mapped parameters are applied to at least one test image to predict a presence of at least one target attribute of the specimen in response to applying the learned parameters. The test image is convert to a selected output image format so as to generate a synthetic image including the predicted at least one attribute. The electronic imaging unit controller performs a material characterization analysis that characterizes the material of the specimen based on the predicted at least one attribute included in the synthetic image.
-
公开(公告)号：US20190050753A1
公开(公告)日：2019-02-14
申请号：US15840132
申请日：2017-12-13
IPC分类号： G06N99/00
CPC分类号： G06N20/00 , G06K9/6262 , G06N3/0454 , G06N3/08
摘要： A sensor system may comprise a sensor; a processor in electronic communication with the sensor; and/or a tangible, non-transitory memory configured to communicate with the processor, the tangible, non-transitory memory having instructions stored thereon that, in response to execution by the processor, cause the processor to perform operations. The operations may comprise recording, by the sensor, a preliminary type data sample; and/or applying, by the processor, a mapping function having a plurality of tuned parameters to the preliminary type data sample, producing a desired type data output.
-
公开(公告)号：US10387803B2
公开(公告)日：2019-08-20
申请号：US15840132
申请日：2017-12-13
摘要： A sensor system may comprise a sensor; a processor in electronic communication with the sensor; and/or a tangible, non-transitory memory configured to communicate with the processor, the tangible, non-transitory memory having instructions stored thereon that, in response to execution by the processor, cause the processor to perform operations. The operations may comprise recording, by the sensor, a preliminary type data sample; and/or applying, by the processor, a mapping function having a plurality of tuned parameters to the preliminary type data sample, producing a desired type data output.
-
公开(公告)号：US20190147283A1
公开(公告)日：2019-05-16
申请号：US16099485
申请日：2016-05-16
摘要： A method includes detecting at least one region of interest in a frame of image data. One or more patches of interest are detected in the frame of image data based on detecting the at least one region of interest. A model including a deep convolutional neural network is applied to the one or more patches of interest. Post-processing of a result of applying the model is performed to produce a post-processing result for the one or more patches of interest. A visual indication of a classification of defects in a structure is output based on the result of the post-processing.
-
-
-
-
-
-
-
-
-
搜索结果
16 条记录 (耗时 0.023 秒)
