-
71.
公开(公告)号:US20180121790A1
公开(公告)日:2018-05-03
申请号:US15854923
申请日:2017-12-27
发明人: Jaeha KIM , Yunju CHOI , Seungheon BAEK
CPC分类号: G06N3/04 , G06N3/0445 , G06N3/0472 , G06N3/063 , G06N3/08 , G06N3/084
摘要: A neural array may include an array unit, a first processing unit, and a second processing unit. The array unit may include synaptic devices. The first processing unit may input a row input signal to the array unit, and receive a row output signal from the array unit. The second processing unit may input a column input signal to the array unit, and receive a column output signal from the array unit. The array unit may have a first array value and a second array value. When the first processing unit or the second processing unit receives an output signal based on the first array value from the array unit which has selected the first array value and then the array unit selects the second array value, it may input a signal generated based on the output signal to the array unit which has selected the second array value.
-
72.
公开(公告)号:US20180121788A1
公开(公告)日:2018-05-03
申请号:US15421424
申请日:2017-01-31
申请人: salesforce.com, inc.
发明人: Kazuma HASHIMOTO , Caiming XIONG , Richard SOCHER
CPC分类号: G06N3/04 , G06F17/20 , G06F17/2705 , G06F17/2715 , G06F17/274 , G06F17/277 , G06F17/2785 , G06N3/0445 , G06N3/0454 , G06N3/0472 , G06N3/063 , G06N3/08 , G06N3/084 , G10L15/16 , G10L15/18 , G10L25/30
摘要: The technology disclosed provides a so-called “joint many-task neural network model” to solve a variety of increasingly complex natural language processing (NLP) tasks using growing depth of layers in a single end-to-end model. The model is successively trained by considering linguistic hierarchies, directly connecting word representations to all model layers, explicitly using predictions in lower tasks, and applying a so-called “successive regularization” technique to prevent catastrophic forgetting. Three examples of lower level model layers are part-of-speech (POS) tagging layer, chunking layer, and dependency parsing layer. Two examples of higher level model layers are semantic relatedness layer and textual entailment layer. The model achieves the state-of-the-art results on chunking, dependency parsing, semantic relatedness and textual entailment.
-
73.
公开(公告)号:US20180121787A1
公开(公告)日:2018-05-03
申请号:US15421407
申请日:2017-01-31
申请人: salesforce.com, inc.
发明人: Kazuma HASHIMOTO , Caiming XIONG , Richard SOCHER
CPC分类号: G06N3/04 , G06F17/20 , G06F17/2705 , G06F17/2715 , G06F17/274 , G06F17/277 , G06F17/2785 , G06N3/0445 , G06N3/0454 , G06N3/0472 , G06N3/063 , G06N3/08 , G06N3/084 , G10L15/16 , G10L15/18 , G10L25/30
摘要: The technology disclosed provides a so-called “joint many-task neural network model” to solve a variety of increasingly complex natural language processing (NLP) tasks using growing depth of layers in a single end-to-end model. The model is successively trained by considering linguistic hierarchies, directly connecting word representations to all model layers, explicitly using predictions in lower tasks, and applying a so-called “successive regularization” technique to prevent catastrophic forgetting. Three examples of lower level model layers are part-of-speech (POS) tagging layer, chunking layer, and dependency parsing layer. Two examples of higher level model layers are semantic relatedness layer and textual entailment layer. The model achieves the state-of-the-art results on chunking, dependency parsing, semantic relatedness and textual entailment.
-
公开(公告)号:US20180114110A1
公开(公告)日:2018-04-26
申请号:US15584611
申请日:2017-05-02
发明人: Seung Ju HAN , Jung Bae KIM , Jae Joon HAN , Chang Kyu CHOI
摘要: A method to reduce a neural network includes: adding a reduced layer, which is reduced from a layer in the neural network, to the neural network; computing a layer loss and a result loss with respect to the reduced layer based on the layer and the reduced layer; and determining a parameter of the reduced layer based on the layer loss and the result loss.
-
75.
公开(公告)号:US20180108165A1
公开(公告)日:2018-04-19
申请号:US15847172
申请日:2017-12-19
发明人: Jianping SHI , Qing LUAN , Qinqin XU , Lei WANG
CPC分类号: G06T11/60 , G06K9/2063 , G06K9/2072 , G06K9/481 , G06K9/6256 , G06K2209/21 , G06N3/0454 , G06N3/08 , G06N3/084 , G06Q30/0251 , G06Q30/0277 , G06T7/60 , G06T7/73 , G06T11/20 , G06T2207/10016
摘要: Embodiments of the present disclosure provide a method and an apparatus for displaying a business object in a video image and an electronic device. The method for displaying a business object in a video image includes: detecting at least one target object from a video image, and determining a feature point of the at least one target object; determining a display position of a to-be-displayed business object in the video image according to the feature point of the at least one target object; and drawing the business object at the display position by using computer graphics. According to the embodiments of the present disclosure, the method and apparatus are conductive to saving network resources and system resources of a client.
-
76.
公开(公告)号:US20180108139A1
公开(公告)日:2018-04-19
申请号:US15788509
申请日:2017-10-19
发明人: Michael Abramoff , Xiaodong Wu
CPC分类号: G06T7/11 , G06N3/0445 , G06N3/0454 , G06N3/084 , G06T2200/04 , G06T2207/10072 , G06T2207/10136 , G06T2207/20081 , G06T2207/20084 , G06T2207/20124
摘要: Disclosed are systems and methods for image segmentation using convolutional networks. Image data comprising an image hypervolume can be received. The image hypervolume can be provided to a trained convolutional neural network (CNN). The CNN can output a segmentation of the image hypervolume.
-
公开(公告)号:US20180107902A1
公开(公告)日:2018-04-19
申请号:US15294773
申请日:2016-10-16
申请人: eBay Inc.
CPC分类号: G06K9/6277 , G06F16/50 , G06F16/532 , G06F16/583 , G06K9/4671 , G06K9/623 , G06K9/6269 , G06N3/0445 , G06N3/0454 , G06N3/084 , G06N5/022 , G06N7/005
摘要: Methods, systems, and computer programs are presented for adding new features to a network service. A method includes receiving an image depicting an object of interest. A category set is determined for the object of interest and an image signature is generated for the image. Using the category set and the image signature, the method identifies a set of publications within a publication database and assigns a rank to each publication. The method causes presentation of the ranked list of publications at a computing device from which the image was received.
-
公开(公告)号:US09947314B2
公开(公告)日:2018-04-17
申请号:US15437490
申请日:2017-02-21
发明人: Liangliang Cao , James J. Fan , Chang Wang , Bing Xiang , Bowen Zhou
IPC分类号: G06F17/27 , G06F17/21 , G10L15/00 , G10L15/06 , G06F17/28 , G10L15/16 , G10L15/18 , G06F17/24 , G06N3/08 , G06N3/04
CPC分类号: G10L15/063 , G06F17/241 , G06F17/28 , G06F17/3069 , G06N3/04 , G06N3/08 , G06N3/084 , G06N3/088 , G06N5/022 , G06N99/005 , G10L15/16 , G10L15/18
摘要: Software that trains an artificial neural network for generating vector representations for natural language text, by performing the following steps: (i) receiving, by one or more processors, a set of natural language text; (ii) generating, by one or more processors, a set of first metadata for the set of natural language text, where the first metadata is generated using supervised learning method(s); (iii) generating, by one or more processors, a set of second metadata for the set of natural language text, where the second metadata is generated using unsupervised learning method(s); and (iv) training, by one or more processors, an artificial neural network adapted to generate vector representations for natural language text, where the training is based, at least in part, on the received natural language text, the generated set of first metadata, and the generated set of second metadata.
-
公开(公告)号:US20180096243A1
公开(公告)日:2018-04-05
申请号:US15282058
申请日:2016-09-30
发明人: Sundeep R PATIL , Ansh KAPIL , Oliver BAPTISTA
CPC分类号: G06N3/084 , G06N3/0454
摘要: The present embodiments relate to a system and method associated with anomaly classification. The method comprises receiving a plurality of time-series data from one or more sensors associated with a machine. The time-series data may be automatically passed through a convolutional neural network to determine reduced dimension data. An anomaly based on classifying the reduced dimension data may be automatically determined. In a case that the anomaly is an unknown anomaly, the determined anomaly may be labeled and the determined anomaly and its associated label may be stored in an anomaly training database.
-
80.
公开(公告)号:US09934364B1
公开(公告)日:2018-04-03
申请号:US15445913
申请日:2017-02-28
发明人: Amit Kumar , John Roop , Anthony J. Campisi
CPC分类号: G16H50/20 , G01N33/57492 , G06F19/20 , G06N3/0454 , G06N3/084 , G16H10/40 , G16H15/00
摘要: The present disclosure provides methods for applying artificial neural networks to flow cytometry data generated from biological samples to diagnose and characterize cancer in a subject.
-
-
-
-
-
-
-
-
-