-
公开(公告)号：US11132180B2
公开(公告)日：2021-09-28
申请号：US16019280
申请日：2018-06-26
摘要： Systems, methods, and computer-executable instructions for guiding program synthesis includes receiving a specification that includes an input and output example. Programs are synthesized that meet the specification. During synthesizing each of the programs includes branching decisions. Each branching decision includes a plurality of paths. Synthesizing the programs comprises includes selecting a first score model, for a first branching decision. Each of the programs is scored using the first score model. The paths of the first branching decision are pared based on the score. One the paths is selected. A synthesized program that meets the specification is returned. The synthesized program includes the one of the paths.
-
公开(公告)号：US20210049442A1
公开(公告)日：2021-02-18
申请号：US16541633
申请日：2019-08-15
发明人： Lekshmi Menon , Amar Budhiraja , Gaurush Hiranandani , Prateek Jain , Darshatkumar Anandji Shah , Ayush Choure , Navya Yarrabelly , Anurag Mishra , Mohammad Luqman , Shivangi Dhakad , Juhi Dua
摘要： Systems and methods for entity recommendation can make use of rich data by allowing the items to be recommended and the recipients of the recommendation (e.g., users) to be modeled as “complex entities” composed of one or more static sub-entities and/or a dynamic component, and by utilizing information about multiple relationships between the sub-entities as reflected in bipartite graphs. Generating recommendations from such information may involve creating vector representations of the sub-entities based on the bipartite graphs (e.g., using graph-based convolutional networks), and combining these vector representations into representations of the items and users (or other recipients) to be fed into a classifier model.
-
公开(公告)号：US20190212989A1
公开(公告)日：2019-07-11
申请号：US16019280
申请日：2018-06-26
CPC分类号： G06F8/33 , G06N3/0427 , G06N3/0445 , G06N3/08
摘要： Systems, methods, and computer-executable instructions for guiding program synthesis includes receiving a specification that includes an input and output example. Programs are synthesized that meet the specification. During synthesizing each of the programs includes branching decisions. Each branching decision includes a plurality of paths. Synthesizing the programs comprises includes selecting a first score model, for a first branching decision. Each of the programs is scored using the first score model. The paths of the first branching decision are pared based on the score. One the paths is selected. A synthesized program that meets the specification is returned. The synthesized program includes the one of the paths.
-
公开(公告)号：US11184301B2
公开(公告)日：2021-11-23
申请号：US16541818
申请日：2019-08-15
发明人： Lekshmi Menon , Amar Budhiraja , Gaurush Hiranandani , Prateek Jain , Darshatkumar Anandji Shah , Ayush Choure , Navya Yarrabelly , Anurag Mishra , Mohammad Luqman , Shivangi Dhakad , Juhi Dua
IPC分类号： G06F15/16 , H04L12/58 , G06F16/901 , G06N3/08
摘要： Systems and methods for entity recommendation can make use of rich data by allowing the items to be recommended and the recipients of the recommendation (e.g., users) to be modeled as “complex entities” composed of one or more static sub-entities and/or a dynamic component, and by utilizing information about multiple relationships between the sub-entities as reflected in bipartite graphs. Generating recommendations from such information may involve creating vector representations of the sub-entities based on the bipartite graphs (e.g., using graph-based convolutional networks), and combining these vector representations into representations of the items and users (or other recipients) to be fed into a classifier model.
-
公开(公告)号：US10554390B2
公开(公告)日：2020-02-04
申请号：US15620034
申请日：2017-06-12
摘要： Systems, methods, and computer-executable instructions for secure data analysis using encrypted data. An encryption key and a decryption key are created. The security of encryption using the encryption key and the decryption key are based upon factoring. A computation key is created based upon the encryption key. Data is encrypted using the encryption key. The encrypted data and the computation key are provided to a remote system. The remote system is requested to perform data analysis on the encrypted data. An encrypted result of the data analysis is received from the remote system. The encrypted result of the data analysis is decrypted with the decryption key.
-
公开(公告)号：US20180359084A1
公开(公告)日：2018-12-13
申请号：US15620034
申请日：2017-06-12
IPC分类号： H04L9/08
CPC分类号： H04L9/08 , G06F7/483 , G06F21/602 , G06F2207/4824 , G06N20/00 , H04L9/008 , H04L9/0816 , H04L9/0838 , H04L9/0894
摘要： Systems, methods, and computer-executable instructions for secure data analysis using encrypted data. An encryption key and a decryption key are created. The security of encryption using the encryption key and the decryption key are based upon factoring. A computation key is created based upon the encryption key. Data is encrypted using the encryption key. The encrypted data and the computation key are provided to a remote system. The remote system is requested to perform data analysis on the encrypted data. An encrypted result of the data analysis is received from the remote system. The encrypted result of the data analysis is decrypted with the decryption key.
-
公开(公告)号：US20180359078A1
公开(公告)日：2018-12-13
申请号：US15620090
申请日：2017-06-12
CPC分类号： H04L9/008 , G06F21/602 , G06N99/005 , H04L63/0428
摘要： Systems, methods, and computer-executable instructions for homomorphic data analysis. Encrypted data is received, from a remote system, that has been encrypted with an encryption key. A number of iterations to iterate over the encrypted data is determined. A model is iterated over by the number of iterations to create an intermediate model. Each iteration updates the model, and the model and the intermediate model encrypted with the encryption key. The intermediate model is provided to the remote system. An updated model based upon the intermediate model is received from the remote system. The updated model is iterated over until a predetermined precision is reached to create a final model. The final model is provided to the remote system. The final model is encrypted with the encryption key.
-
公开(公告)号：US11886971B2
公开(公告)日：2024-01-30
申请号：US16541633
申请日：2019-08-15
发明人： Lekshmi Menon , Amar Budhiraja , Gaurush Hiranandani , Prateek Jain , Darshatkumar Anandji Shah , Ayush Choure , Navya Yarrabelly , Anurag Mishra , Mohammad Luqman , Shivangi Dhakad , Juhi Dua
摘要： Systems and methods for entity recommendation can make use of rich data by allowing the items to be recommended and the recipients of the recommendation (e.g., users) to be modeled as “complex entities” composed of one or more static sub-entities and/or a dynamic component, and by utilizing information about multiple relationships between the sub-entities as reflected in bipartite graphs. Generating recommendations from such information may involve creating vector representations of the sub-entities based on the bipartite graphs (e.g., using graph-based convolutional networks), and combining these vector representations into representations of the items and users (or other recipients) to be fed into a classifier model.
-
公开(公告)号：US20180330275A1
公开(公告)日：2018-11-15
申请号：US15623661
申请日：2017-06-15
CPC分类号： G06N99/005 , G06N5/04
摘要： Generally discussed herein are devices, systems, and methods for machine-learning. A method may include training, based on sparseness constraints and using a first device, a sparse matrix, prototype vectors, prototype labels, and corresponding prototype score vectors, simultaneously, storing the sparse matrix, prototype vectors, and prototype labels on a random-access memory (RAM) of a second device, projecting, using the second device, a prediction vector of a second dimensional space to the first dimensional space, the first dimensional space less than the second dimensional space, determining whether the projected prediction vector is closer to the one or more first prototype vectors or the one or more second prototype vectors, and determining a prediction by identifying the which prediction outcome the projected prediction vector is closer to.
-
公开(公告)号：US11210327B2
公开(公告)日：2021-12-28
申请号：US16448805
申请日：2019-06-21
IPC分类号： G06F16/35 , G06F40/151 , G06F40/211
摘要： A computing device includes a storage machine holding instructions executable by a logic machine to generate multi-string clusters, each containing alphanumeric strings of a dataset. Further multi-string clusters are generated via iterative performance of a combination operation in which a hierarchically-superior cluster is generated from a set of multi-string clusters. The combination operation includes, for candidate pairs of multi-string clusters, generating syntactic profiles describing an alphanumeric string from each multi-string cluster of the candidate pair. For each of the candidate pairs, a cost factor is determined for at least one of its syntactic profiles. Based on the cost factors determined for the syntactic profiles, one of the candidate pairs is selected. The multi-string clusters from the selected candidate pair are combined to generate the hierarchically-superior cluster including all of the alphanumeric strings from the selected candidate pair of multi-string clusters.
-
-
-
-
-
-
-
-
-
搜索结果
12 条记录 (耗时 0.02 秒)
