专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

91. 发明申请

WO2023060150A1 DATA COMPRESSION TECHNIQUES FOR MACHINE LEARNING MODELS 审中-公开
公开(公告)号：WO2023060150A1
公开(公告)日：2023-04-13
申请号：PCT/US2022/077637
申请日：2022-10-06
申请人： EQUIFAX INC.
发明人： GUO, Bo , BONDUGULA, Rajkumar
IPC分类号： G06N3/02 , G06N3/088 , G06N5/022 , G06N20/00 , G06N3/084 , G06F18/2148 , G06N5/01
摘要： In some aspects, techniques for creating representative and informative training datasets for the training of machine-learning models are provided. For example, a risk assessment system can receive a risk assessment query for a target entity. The risk assessment system can compute an output risk indicator for the target entity by applying a machine learning model to values of informative attributes associated with the target entity. The machine learning model may be trained using training samples selected from a representative and informative (RAI) dataset. The RAI dataset can be created by determining the informative attributes based on attributes used by a set of models and further extracting representative data records from an initial training dataset based on the determined informative attributes. The risk assessment system can transmit a responsive message including the output risk indicator for use in controlling access of the target entity to an interactive computing environment.

92. 发明申请

WO2023056554A1 DEEP-LEARNING BASED SYSTEM FOR ONLINE APPLICATION ORIGINATION (OAO) FRAUD DETECTION 审中-公开
公开(公告)号：WO2023056554A1
公开(公告)日：2023-04-13
申请号：PCT/CA2022/051471
申请日：2022-10-05
申请人： MASTERCARD TECHNOLOGIES CANADA ULC
发明人： KUMAR, Ashish , VERMA, Sangam , BHOWMIK, Tanmoy , SINGH, Karamjit , HEARTY, John , CHAN, Sik Suen
IPC分类号： G06F21/50 , G06N20/00 , G06N3/045 , G06N3/088 , G06Q40/03
摘要： A fraud prevention server that includes an electronic processor and a memory. The memory includes an online application origination (OAO) service and a plurality of OAO models, each of the plurality of OAO models differentiates between a behavior of a normal user and a behavior of a nefarious actor during a submission of the online application on a device. When executing the OAO service, the electronic processor is configured to receive form data from a client server, determine a best OAO model from a plurality of OAO models with deep-learning, determine a fraud score of the online application based on the best OAO model, and control the client server to approve, hold, or deny the online application based on the fraud score that is determined.

93. 发明申请

WO2023278196A1 AUTOMATIC LOCALIZED EVALUATION OF CONTOURS WITH VISUAL FEEDBACK 审中-公开
公开(公告)号：WO2023278196A1
公开(公告)日：2023-01-05
申请号：PCT/US2022/034253
申请日：2022-06-21
申请人： VARIAN MEDICAL SYSTEMS, INC.
发明人： SAWKEY, Daren
IPC分类号： G06T7/00 , G06K9/62 , G06F18/214 , G06F18/217 , G06N3/045 , G06N3/088 , G06T11/203 , G06T2200/24 , G06T2207/10072 , G06T2207/10081 , G06T2207/10088 , G06T2207/10104 , G06T2207/10116 , G06T2207/20081 , G06T2207/20084 , G06T2207/20104 , G06T2207/30004 , G06T2207/30016 , G06T2207/30096 , G06T2207/30168 , G06T7/0012 , G06T7/11 , G06T7/12 , G06V10/46 , G06V10/752 , G06V10/774 , G06V10/778 , G06V10/82 , G06V2201/031 , G16H15/00 , G16H30/20 , G16H30/40 , G16H40/20 , G16H50/20
摘要： A localized evaluation network incorporates a discriminator (111a) acting as classifier, which may be included within a generative adversarial network, GAN (111). GAN (111) may include a generative network such as U-NET for creating segmentations. The localized evaluation network is trained on image pairs (220) including medical images of organs of interest and segmentation (mask) images. The network is trained to distinguish whether an image pair (220) does or does not represent the ground truth. GAN (111) examines interior layers of the discriminator (111a) and evaluates how much each localized image region contributes to the final classification. The discriminator (111a) may analyze regions of the image pair (220) that contribute to a classification by analyzing layer weights of the machine learning model.

94. 发明申请

WO2023278190A1 METHOD FOR DETERMINING CORRECTIVE FILM PATTERN TO REDUCE SEMICONDUCTOR WAFER BOW 审中-公开
公开(公告)号：WO2023278190A1
公开(公告)日：2023-01-05
申请号：PCT/US2022/034138
申请日：2022-06-20
申请人： TIGNIS, INC.
发明人： STODDARD, Ryan, J. , HERLOCKER, Jonathan, L. , MCLAUGHLIN, Matt
IPC分类号： H01L21/67 , G06N20/00 , G06V10/82 , G06N3/045 , G06N3/088 , H01L21/67288
摘要： A method is disclosed for generating a corrective film pattern for reducing wafer bow in a semiconductor wafer fabrication process. The method inputs to a neural network [150] a wafer bow signature [152] for a predetermined semiconductor fabrication step. The neural network [150] generates from the input a corrective film pattern [154] corresponding to the wafer bow signature. The neural network is trained with a training dataset of wafer shape transformations [104] and corresponding corrective film patterns [106].

95. 发明申请

WO2022271794A1 SEMI-AUTONOMOUS ADVERTISING SYSTEMS AND METHODS 审中-公开
公开(公告)号：WO2022271794A1
公开(公告)日：2022-12-29
申请号：PCT/US2022/034477
申请日：2022-06-22
申请人： Z2 COOL COMICS LLC
发明人： ZELENBERG, Aleksey
IPC分类号： G06Q30/02 , G06N3/08 , G06N5/02 , G06N3/088 , G06Q30/0244
摘要： Embodiments of the present disclosure provide improved methods, systems, devices, media, techniques, and processes, often computer-based and/ or processor- based, for advertising to consumers, such as consumers of music-based products. In a first part of the disclosed methods and systems, potential sales of a product can be predicted. In a second part of the disclosed methods and systems, one or more regression strategies can be used to analyze data from previous products in order to produce optimi zed parameter values. In a third part of the disclosed methods and systems, adverti sement performance can be monitored and input parameters adj usted based on that performance.

96. 发明申请

WO2022212189A1 DATA-EFFICIENT PHOTOREALISTIC 3D HOLOGRAPHY 审中-公开
公开(公告)号：WO2022212189A1
公开(公告)日：2022-10-06
申请号：PCT/US2022/021853
申请日：2022-03-25
申请人： MASSACHUSETTS INSTITUTE OF TECHNOLOGY
发明人： MATUSIK, Wojciech , SHI, Liang
IPC分类号： G03H1/08 , G03H1/32 , G03H1/22 , G03H1/0808 , G03H2001/0816 , G03H2001/0858 , G03H2001/0883 , G03H2001/2271 , G03H2210/36 , G03H2210/454 , G03H2225/32 , G03H2225/33 , G06N3/0454 , G06N3/088 , G06N7/005
摘要： A number of techniques provide a data efficient and/or computation efficient computer- generated holography, examples of which may be implemented on low-power devices such as smartphones and virtual-reality/augmented-reality devices and provide high fidelity holographic images. The techniques include used of layered depth image representations and end-to-end training of neural network generation of double-phase hologram encoding.

97. 发明申请

WO2022119811A1 HEALTH MONITORING SYSTEM 审中-公开
公开(公告)号：WO2022119811A1
公开(公告)日：2022-06-09
申请号：PCT/US2021/061137
申请日：2021-11-30
申请人： INNSIGHTFUL, INC.
发明人： EHSANI, Farzad , MASTER, Demitrios, L.
IPC分类号： G06N3/00 , G06N3/02 , G06N3/08 , G16H10/00 , G06N20/00 , G06N3/045 , G06N3/088 , G16H40/63 , G16H40/67 , G16H50/20 , G16H50/70
摘要： A system for health monitoring comprised of one or more neural networks. A first function of the one or more neural networks includes an autoencoder functionality, tuned to have high recall, configured for monitoring data and for detecting an anomaly within the data. A second function of the one or more neural networks is a false positive reduction (FPR) function, configured for distinguishing false positive anomalies from true positive anomalies by analyzing the data or querying an individual. Confirmed positive anomalies are classified by a classification engine. The system may be configured to train one or more machine learning models thereof, such that the system is trained for monitoring of the individual.

98. 发明申请

WO2022078573A1 DATA PRUNING TOOL AND RELATED ASPECTS 审中-公开
公开(公告)号：WO2022078573A1
公开(公告)日：2022-04-21
申请号：PCT/EP2020/078661
申请日：2020-10-12
申请人： TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
发明人： SHARMA, Prashant , REXBERG, Leonard
IPC分类号： G06N3/08 , G06N3/088
摘要： A method and related aspects are disclosed for determining one or more regions of interest in a multi-dimensional data set comprising a plurality of parameter sets, each parameter set comprising a parameter set identifier, a plurality of dimensions of selection conditions for assessing a configurable physical entity, and an indication of an assessed characteristic of the configurable physical entity. The method comprises at least mapping, using a self-organising map, SOM, model which uses competitive group learning, the multi-dimensional data set onto an edge-connected surface mesh of neurons; identifying at least one cluster of neurons on the surface mesh based on a category of the assessed characteristic; identifying a set of ranges of boundary values for the selection conditions for each cluster, each range of boundary values comprising a maximum and a minimum weight value of the weights representing that selection condition of the neurons in that cluster; and determining one or more regions of interest which associate the boundary values of the selection conditions of each cluster with one or more test case identifiers for the test cases represented by the neurons in that cluster. The method may be implemented in some embodiments as a data pruning tool.

99. 发明申请

WO2022011231A1 ESCAPE PROFILING FOR THERAPEUTIC AND VACCINE DEVELOPMENT 审中-公开
公开(公告)号：WO2022011231A1
公开(公告)日：2022-01-13
申请号：PCT/US2021/041044
申请日：2021-07-09
申请人： HIE, Brian , LEIGHTON, Bonnie Berger , BRYSON, Bryan D.
发明人： HIE, Brian , LEIGHTON, Bonnie Berger , BRYSON, Bryan D.
IPC分类号： G16B40/30 , G06N3/04 , G06N3/08 , G16B30/00 , G06N3/0445 , G06N3/0454 , G06N3/088 , G16B15/30 , G16B40/20
摘要： A method of viral escape profiling is used in association with antiviral or vaccine development. The method begins by training a language-based model against training data comprising a corpus of viral protein sequences of a given viral protein to model a viral escape profile. The viral escape profile represents, for one or more regions of the given viral protein, a relative viral escape potential of a mutation, the relative viral escape potential being derived as a function that combines both "semantic change," representing a degree to which the mutation is recognized by the human immune system (i.e., antigenic change), and "grammaticality,"representing a degree to which the mutation affects viral infectivity (i.e. viral fitness). Using the model, a region of the given viral protein having an escape potential of interest is identified. Information regarding the region is then output to a vaccine or anti-viral therapeutic design and development workflow.

100. 发明申请

WO2021245292A1 GENERATING AUDIO DATA USING UNALIGNED TEXT INPUTS WITH AN ADVERSARIAL NETWORK 审中-公开
公开(公告)号：WO2021245292A1
公开(公告)日：2021-12-09
申请号：PCT/EP2021/065195
申请日：2021-06-07
申请人： DEEPMIND TECHNOLOGIES LIMITED
发明人： DONAHUE, Jeffrey , SIMONYAN, Karen , DIELEMAN, Sander Etienne Lea , BINKOWSKI, Mikolaj , ELSEN, Erich Konrad
IPC分类号： G06N3/04 , G06N3/08 , G10L13/00 , G06N3/0454 , G06N3/0481 , G06N3/088 , G10L13/02 , G10L13/047 , G10L2013/105 , G10L25/30
摘要： Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a generative neural network to convert conditioning text inputs to audio outputs. The generative neural network includes an alignment neural network that is configured to receive a generative input that includes the conditioning text input and to process the generative input to generate an aligned conditioning sequence that comprises a respective feature representation at each of a plurality of first time steps and that is temporally aligned with the audio output.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式