公开(公告)号：WO2019152020A1

公开(公告)日：2019-08-08

申请号：PCT/US2018/016238

申请日：2018-01-31

申请人： NIU, Yuezhen ,  NEVEN, Hartmut ,  SMELYANSKIY, Vadim ,  CASTRILLO, Sergio Boixo

发明人： NIU, Yuezhen ,  NEVEN, Hartmut ,  SMELYANSKIY, Vadim ,  CASTRILLO, Sergio Boixo

IPC分类号： G06N99/00 ,  G06N3/00 ,  G06N3/04 ,  G06N3/08

CPC分类号： G06N3/0454 ,  G06N3/006 ,  G06N3/084 ,  G06N10/00

摘要： Methods, systems, and apparatus for designing a quantum control trajectory for implementing a quantum gate using quantum hardware. In one aspect, a method includes the actions of representing the quantum gate as a sequence of control actions and applying a reinforcement learning model to iteratively adjust each control action in the sequence of control actions to determine a quantum control trajectory that implements the quantum gate and reduces leakage, infidelity and total runtime of the quantum gate to improve its robustness of performance against control noise during the iterative adjustments.

公开(公告)号：WO2019108625A1

公开(公告)日：2019-06-06

申请号：PCT/US2018/062807

申请日：2018-11-28

申请人： KNOWBE4, INC.

发明人： SITES, Eric

IPC分类号： H04L29/06

CPC分类号： H04L63/1483 ,  G06F21/552 ,  G06F21/577 ,  G06N3/0445 ,  G06N3/0472 ,  G06N3/082 ,  G06N3/084 ,  H04L63/1491

摘要： The present disclose describes systems and methods for creating a simulated phishing campaign for a user based on at least a history of the user with respect to simulated phishing campaigns. A database may be configured to store simulated phishing campaign history of a user, the simulated phishing campaign history comprising information on events associated with the user during one or more previous simulated phishing campaigns, A campaign controller may identify the simulated phishing campaign history of the user from the database, determine based at least on the simulated phishing campaign history of the user, a model from a plurality of models for creating a simulated phishing campaign directed to the user; and create, responsive to the determination, the simulated phishing campaign using the model.

公开(公告)号：WO2019096952A1

公开(公告)日：2019-05-23

申请号：PCT/EP2018/081466

申请日：2018-11-15

申请人： NEC LABORATORIES EUROPE GMBH

发明人： OÑORO RUBIO, Daniel ,  NIEPERT, Mathias

IPC分类号： G06K9/00 ,  G06K9/62

CPC分类号： G06T7/0002 ,  G06F17/11 ,  G06K9/00771 ,  G06K9/3233 ,  G06K9/6267 ,  G06N3/0454 ,  G06N3/0481 ,  G06N3/08 ,  G06N3/084 ,  G06T2207/30242

摘要： A method for object density monitoring includes receiving, by a processing server, an input image captured by an image sensor. The method further includes providing an annotated dataset with a target object to be identified in the input image, and providing, by the processing server as output, an object density map generated from the input image. The processing server provides the object density map by using a deep neural network having one or more pairs of a compression layer and a decompression layer connected by gated shortcuts.

公开(公告)号：WO2019094882A1

公开(公告)日：2019-05-16

申请号：PCT/US2018/060611

申请日：2018-11-13

申请人： RAYTHEON COMPANY

发明人： GOULDING, John R. ,  MIXTER, John E. ,  MUCHA, David R. ,  GANGWER, Troy A. ,  SILVA, Ryan D.

IPC分类号： G06N3/063 ,  G06N3/04 ,  G06N3/08

CPC分类号： G06N3/084 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/063

摘要： Processing circuitry for a deep neural network can include input/output ports, and a plurality of neural network layers coupled in order from a first layer to a last layer, each of the plurality of neural network layers including a plurality of weighted computational units having circuitry to interleave forward propagation of computational unit input values from the first layer to the last layer and backward propagation of output error values from the last layer to the first layer.

公开(公告)号：WO2019094857A1

公开(公告)日：2019-05-16

申请号：PCT/US2018/060271

申请日：2018-11-12

申请人： THE TRUSTEES OF COLUMBIA UNIVERISTY IN THE CITY OF NEW YORK ,  UNIVERSITY OF CALIFORNIA SAN FRANCISCO

发明人： HA, Richard ,  CHANG, Peter

IPC分类号： G06N3/00 ,  G06N3/02 ,  G06N3/04 ,  G06N3/06 ,  G06N3/08

CPC分类号： G06N3/0454 ,  G06N3/0481 ,  G06N3/084

摘要： An exemplary system, method and computer-accessible medium for determining a risk of developing breast cancer for a patient(s) can include, for example receiving an image(s) of an internal portion(s) of a breast of the patient(s), and determining the risk by applying a neural network(s) to the image(s). The neural network can be a convolutional neural network (CNN). The CNN can include a plurality of layers. Each of the layers can have a different number of feature channels. The CNN can include at least four layers. A first layer of the at least four layers can have 256x256x16 feature channels, a second layer of the at least four layers can have 128x128x32 feature channels, a third layer of the at least four layers can have 64x64x64 feature channels, and a fourth layer of the at least four layers can have 32x32x128 feature channels.

公开(公告)号：WO2019089553A1

公开(公告)日：2019-05-09

申请号：PCT/US2018/058162

申请日：2018-10-30

申请人： WAVE COMPUTING, INC.

发明人： SHIRING, Kenneth ,  JOHNSON, Stephen, Curtis

IPC分类号： G06N3/04 ,  G06N3/08 ,  G06N3/063

CPC分类号： G06N3/0454 ,  G06N3/0481 ,  G06N3/063 ,  G06N3/082 ,  G06N3/084

摘要： Techniques are disclosed for tensor radix point calculation in a neural network. A first tensor is obtained. A first set of weights is generated for the first tensor. An operation is evaluated to be performed by a layer within a deep neural network on the first tensor using the first set of weights. A set of output radix points is determined for the layer within the deep neural network based on the first tensor and the operation. An output tensor is calculated for the layer within the deep neural network using the set of output radix points, the first tensor, and the first set of weights. The operation is restarted, when the layer reports a hardware overflow, using an updated set of output radix points. The determining is further based on a radix point for the first tensor. The determining is further based on metadata for the first tensor.

公开(公告)号：WO2019068616A1

公开(公告)日：2019-04-11

申请号：PCT/EP2018/076598

申请日：2018-10-01

申请人： IMEC VZW ,  JANSSEN PHARMACEUTICA NV ,  KATHOLIEKE UNIVERSITEIT LEUVEN

发明人： CEULEMANS, Hugo ,  WUYTS, Roel ,  VERACHTERT, Wilfried ,  SIMM, Jaak ,  ARANY, Adam ,  MOREAU, Yves Jean Luc ,  HERZEEL, Charlotte

IPC分类号： G06N20/00 ,  G06N3/08 ,  G16H10/60

CPC分类号： G06N3/0427 ,  G06F21/6218 ,  G06F21/6245 ,  G06N3/04 ,  G06N3/084 ,  G16C20/30 ,  G16C20/70 ,  G16H10/60

摘要： The present disclosure relates to secure broker-mediated data analysis and prediction. One example embodiment includes a method. The method includes receiving, by a managing computing device, a plurality of datasets from client computing devices. The method also includes computing, by the managing computing device, a shared representation based on a shared function having one or more shared parameters. Further, the method includes transmitting, by the managing computing device, the shared representation and other data to the client computing devices. In addition, the method includes, based on the shared representation and the other data, the client computing devices update partial representations and individual functions with one or more individual parameters. Still further, the method includes determining, by the client computing devices, feedback values to provide to the managing computing device. Additionally, the method includes updating, by the managing computing device, the one or more shared parameters based on the feedback values.

公开(公告)号：WO2019056470A1

公开(公告)日：2019-03-28

申请号：PCT/CN2017/107809

申请日：2017-10-26

申请人： 平安科技(深圳)有限公司

发明人： 吴壮伟 ,  金鑫 ,  张川

IPC分类号： G06K9/62

CPC分类号： G06K9/6256 ,  G06N3/084

摘要： 一种驾驶模型训练方法、驾驶人识别方法、装置、设备及介质。该驾驶模型训练方法包括：获取用户的训练行为数据，所述训练行为数据与用户标识相关联（S11）；基于所述训练行为数据，获取与所述用户标识相关联的训练驾驶数据（S12）；基于所述用户标识，从所述训练驾驶数据获取正负样本（S13）；采用所述正负样本对误差反向传播神经网络模型进行训练，获取目标驾驶模型（S14）。该驾驶模型训练方法解决了当前驾驶模型识别效果较差的问题，并提高了识别驾驶人开车的精确度。

公开(公告)号：WO2019023372A1

公开(公告)日：2019-01-31

申请号：PCT/US2018/043740

申请日：2018-07-25

申请人： RIPPLE LABS INC.

发明人： THOMAS, Stefan ,  KREY, Peter

IPC分类号： G06Q20/02 ,  G06Q20/10 ,  G06Q20/40

CPC分类号： G06Q30/0185 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/08 ,  G06N3/084 ,  G06N7/005

摘要： Systems and techniques are provided for electronic payment network security. Payment data including an origin and a destination for a payment in an electronic payment network may be received. A route of the payment in the electronic payment network may be estimated based on the origin and the destination. The estimated route of the payment in the electronic payment network may be input to a neural network. Fraud probabilities may be determined using the neural network. A fraud probability may include a value indicating a probability of fraud in the payment in the electronic payment network.

公开(公告)号：WO2019015889A1

公开(公告)日：2019-01-24

申请号：PCT/EP2018/065786

申请日：2018-06-14

申请人： MEMSOURCE A.S.

发明人： ČANĚK, David ,  FRÍVALDSKÝ, Dalibor ,  TAMCHYNA, Aleš

IPC分类号： G06F17/28 ,  G06F17/27 ,  G06N3/04 ,  G06N3/08

CPC分类号： G06F17/289 ,  G06F17/278 ,  G06F17/2818 ,  G06F17/2827 ,  G06F17/2836 ,  G06F17/2845 ,  G06F17/2854 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/082 ,  G06N3/084 ,  G06N20/00

摘要： A translation server computer and related methods are described. The translation server computer is programmed or configured to create computer-implemented techniques for classifying segments in a source language as non-translatable into a target language, nearly-translatable into the target language, or otherwise, and for generating translations in the target language for the segments classified as nearly-translatable. The translation server computer is further programmed or configured to apply the computer-implemented techniques on an input document to generate a classification and a translation when appropriate for each segment in the document, and cause a user computer to display the translations and classifications.