专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20190073565A1 AUTOMATED AND UNSUPERVISED GENERATION OF REAL-WORLD TRAINING DATA 审中-公开
公开(公告)号：US20190073565A1
公开(公告)日：2019-03-07
申请号：US16122695
申请日：2018-09-05
申请人： SENTIENT TECHNOLOGIES (BARBADOS) LIMITED
发明人： Antoine SALIOU
IPC分类号： G06K9/62 , G06K9/00 , G06N3/08
CPC分类号： G06K9/6257 , G06K9/00744 , G06K9/6252 , G06K9/6263 , G06N3/0454 , G06N3/08 , G06N3/084 , G06N3/088
摘要： The technology disclosed uses a combination of an object detector and an object tracker to process video sequences and produce tracks of real-world images categorized by objects detected in the video sequences. The tracks of real-world images are used to iteratively train and re-train the object detector and improve its detection rate during a so-called “training cycle”. Each training cycle of improving the object detector is followed by a so-called “training data generation cycle” that involves collaboration between the improved object detector and the object tracker. Improved detection by the object detector causes the object tracker to produce longer and smoother tracks tagged with bounding boxes around the target object. Longer and smoother tracks and corresponding bounding boxes from the last training data generation cycle are used as ground truth in the current training cycle until the object detector's performance reaches a convergence point.

2. 发明授权

US10025700B1 Data mining technique with n-Pool evolution 有权
公开(公告)号：US10025700B1
公开(公告)日：2018-07-17
申请号：US15071016
申请日：2016-03-15
申请人： SENTIENT TECHNOLOGIES (BARBADOS) LIMITED
发明人： Hormoz Shahrzad , Kaivan Kamali , Babak Hodjat , Daniel Edward Fink
IPC分类号： G06F11/36 , G06F17/30
摘要： Roughly described, a training database contains N segments of data samples. Candidate individuals identify a testing experience level, a fitness estimate, a rule set, and a testing set TSi of the data samples on which it is tested. The testing sets have fewer than all of the data segments and they are not all the same. Testing involves testing on only the individual's assigned set of data segments, updating the fitness estimates and testing experience levels, and discarding candidates through competition. If an individual reaches a predetermined maturity level of testing experience, then validating involves further testing it on samples of the testing data from a testing data segment other than those in the individual's testing set TSi. Those individuals that satisfy validation criteria are considered for deployment.

3. 发明授权

US09684875B1 Data mining technique with experience-layered gene pool 有权
公开(公告)号：US09684875B1
公开(公告)日：2017-06-20
申请号：US14539908
申请日：2014-11-12
申请人： SENTIENT TECHNOLOGIES (BARBADOS) LIMITED
发明人： Babak Hodjat , Hormoz Shahrzad , Greg S. Hornby
IPC分类号： G06N99/00
CPC分类号： G06F17/30539 , G06N3/126 , G06N99/005
摘要： Roughly described, a computer-implemented evolutionary data mining system includes a memory storing a candidate gene database in which each candidate individual has a respective fitness estimate; a gene pool processor which tests individuals from the candidate gene pool on training data and updates the fitness estimate associated with the individuals in dependence upon the tests; and a gene harvesting module providing for deployment selected ones of the individuals from the gene pool, wherein the gene pool processor includes a competition module which selects individuals for discarding from the gene pool in dependence upon both their updated fitness estimate and their testing experience level. Preferably the gene database has an elitist pool containing multiple experience layers, and the competition module causes individuals to compete only with other individuals in their same experience layer.

4. 发明申请

US20170091319A1 BAYESIAN VISUAL INTERACTIVE SEARCH 审中-公开
公开(公告)号：US20170091319A1
公开(公告)日：2017-03-30
申请号：US15373897
申请日：2016-12-09
申请人： SENTIENT TECHNOLOGIES (BARBADOS) LIMITED
发明人： Diego Guy M. Legrand , Philip M. Long , Nigel Duffy , Olivier Francon
IPC分类号： G06F17/30 , G06N5/02
CPC分类号： G06F17/30687 , G06F17/30011 , G06F17/30958 , G06F17/30994 , G06N5/022 , G06Q30/00
摘要： A method for identifying a desired document is provided to include calculating a Prior probability score for each document of a candidate list including a portion of documents of an embedding space, the Prior probability score indicating a preliminary probability, for each document of the candidate list, that the document is the desired document, and identifying an initial (i=0) collection of N0>1 candidate documents from the candidate list in dependence on the calculated Prior probability scores, the initial collection of candidate documents having fewer documents than the candidate list. The method further includes, for each i'th iteration in a plurality of iterations, beginning with a first iteration (i=1) and in response to user selection of an i'th selected document from the (i−1)'th collection of candidate documents, identifying an i'th collection of Ni>1 candidate documents from the candidate list in dependence on Posterior probability scores.

5. 发明授权

US09466023B1 Data mining technique with federated evolutionary coordination 有权
标题翻译：数据挖掘技术与联合进化协调
公开(公告)号：US09466023B1
公开(公告)日：2016-10-11
申请号：US14011062
申请日：2013-08-27
申请人： SENTIENT TECHNOLOGIES (BARBADOS) LIMITED
发明人： Hormoz Shahrzad , Babak Hodjat
IPC分类号： G06N3/08
CPC分类号： G06N3/086 , G06F9/5066 , G06F2209/5017 , G06N3/126 , G06Q10/0633
摘要： Roughly described, a data mining arrangement for developing high quality classifiers using an evolutionary algorithm, includes a plurality of “mid-chain” evolutionary coordinators, down-chain of a main (top-chain) evolutionary coordinator and up-chain of evolutionary engines. Multiple levels of mid-chain evolutionary coordinators can be used in a hierarchy, and the various branches of the hierarchy need not have equal length. Each evolutionary coordinator (other than the top-chain evolutionary coordinator) appears to its up-chain neighbor as if it were an evolutionary engine, though it does not actually perform any evolution itself. Similarly, each evolutionary coordinator (including the top-chain evolutionary coordinator) also appears to its down-chain neighbors as a top-chain evolutionary coordinator. Each mid-chain evolutionary coordinator maintains its own local candidate pool, reducing the load on the top-chain evolutionary coordinator pool, as well as reducing bandwidth requirements. Only the evolutionary engines perform actual testing of candidate individuals on training data.
摘要翻译：粗略地描述，使用进化算法开发高质量分类器的数据挖掘安排包括多个“中链”进化协调器，下游链（主链）进化协调器和进化引擎的上链。可以在层次结构中使用多级中级进化协调器，并且层次结构的各种分支不需要具有相等的长度。每个进化协调器（除了顶级进化协调器之外）似乎都是其上链邻居，就像它是一个进化引擎一样，尽管它实际上并不执行任何进化本身。同样，每个进化协调员（包括顶级进化协调员）在其下游邻居中似乎也是顶级进化协调员。每个中链进化协调器维护自己的本地候选池，减少顶级进化协调器池的负载，并减少带宽需求。只有进化引擎对候选人进行培训数据的实际测试。

6. 发明授权

US09304895B1 Evolutionary technique with n-pool evolution 有权
标题翻译：具有n池进化的进化技术
公开(公告)号：US09304895B1
公开(公告)日：2016-04-05
申请号：US13945630
申请日：2013-07-18
申请人： SENTIENT TECHNOLOGIES (BARBADOS) LIMITED
发明人： Hormoz Shahrzad , Kaivan Kamali , Babak Hodjat , Daniel Edward Fink
IPC分类号： G06F11/36 , G06F17/30
CPC分类号： G06F11/3692 , G06F11/3668 , G06F17/30477 , G06F17/30572
摘要： Roughly described, a training database contains N segments of data samples. Candidate individuals identify a testing experience level, a fitness estimate, a rule set, and a testing set TSi of the data samples on which it is tested. The testing sets have fewer than all of the data segments and they are not all the same. Testing involves testing on only the individual's assigned set of data segments, updating the fitness estimates and testing experience levels, and discarding candidates through competition. If an individual reaches a predetermined maturity level of testing experience, then validating involves further testing it on samples of the testing data from a testing data segment other than those in the individual's testing set TSi. Those individuals that satisfy validation criteria are considered for deployment.
摘要翻译：粗略描述，训练数据库包含N个数据样本段。候选人确定测试经验水平，适应度估计，规则集和测试集合的测试集TSi。测试集比所有数据段少，并不完全相同。测试包括仅对个人分配的数据段进行测试，更新健身评估和测试体验水平，并通过竞争来抛弃候选人。如果个人达到预定的成熟度水平的测试经验，则验证将进一步测试来自测试数据的测试数据样本，而不是个体测试集TSi中的测试数据段。满足验证标准的那些人员被考虑部署。

7. 发明申请

US20180253408A1 AUTONOMOUS CONFIGURATION OF CONVERSION CODE TO CONTROL DISPLAY AND FUNCTIONALITY OF WEBPAGE PORTIONS 审中-公开
公开(公告)号：US20180253408A1
公开(公告)日：2018-09-06
申请号：US15911050
申请日：2018-03-02
申请人： SENTIENT TECHNOLOGIES (BARBADOS) LIMITED
发明人： Robert Severn
IPC分类号： G06F17/22 , H04L12/24 , G06F3/0484 , G06N3/08
摘要： The technology disclosed is generally directed to massively multivariate testing, conversion rate optimization, and product recommendation and, in particular, directed to automatically and autonomously placing conversion code (e.g., scripts) in webpages of a host website without requiring any affirmative action on the part of the host. The conversion code modifies display and functionality of a particular portion of a host webpage without modifying other portions of the host webpage. The conversion code is placed by a website modification service which is limitedly authorized by the host to modify only the particular portion of the host webpage under a product recommendation and/or conversion rate optimization scheme.

8. 发明申请

US20180250554A1 Behavior Dominated Search in Evolutionary Search Systems 审中-公开
公开(公告)号：US20180250554A1
公开(公告)日：2018-09-06
申请号：US15912475
申请日：2018-03-05
申请人： SENTIENT TECHNOLOGIES (BARBADOS) LIMITED
发明人： Elliot Meyerson , Risto Miikkulainen
IPC分类号： A63B24/00 , G06F17/30
CPC分类号： A63B24/0062 , A63B2024/0065 , A63B2024/0068 , G06F16/23 , G16H20/30
摘要： Roughly described, a computer system uses a behavior-driven algorithm that is better able to find optimum solutions to a problem by balancing the use of fitness and novelty measures in evolutionary optimization. In competition among candidate individuals, a domination estimate between a pair of individuals is determined by both their fitness estimate difference and their behavior difference relative to one another. An increase in the fitness estimate difference of one individual of the pair over the other increases the domination estimate of the first individual. An increase in the behavior distance between the pair of individuals decreases the domination estimate of both of the individuals. Individuals with a higher domination estimate are more likely to survive competitions among the candidate individuals.

9. 发明申请

US20180137143A1 Data Object Creation and Recommendation Using Machine Learning Based Offline Evolution 审中-公开
公开(公告)号：US20180137143A1
公开(公告)日：2018-05-17
申请号：US15813019
申请日：2017-11-14
申请人： Sentient Technologies (Barbados) Limited
发明人： Myles BRUNDAGE , Risto MIIKKULAINEN
IPC分类号： G06F17/30 , G06N99/00 , G06K9/62
CPC分类号： G06F16/5838 , G06F16/583 , G06F16/5854 , G06K9/00624 , G06K9/4628 , G06K9/6215 , G06K9/6253 , G06K9/6255 , G06K9/6257 , G06K9/626 , G06K9/6262 , G06K9/6271 , G06N3/0454 , G06N3/084 , G06N3/086 , G06N20/00
摘要： The technology disclosed relates to neural network-based systems and methods of preparing a data object creation and recommendation database. Roughly described, it relates to, for each of a plurality of preliminary data object images, providing a representation of the image in conjunction with a respective conformity parameter indicating level of conformity of the image with a predefined goal, training a neural network system with the preliminary data object image representations in conjunction with their respective conformity parameters, to evaluate future data object image representations for conformity with the predefined goal, selecting a subset of secondary data object image representations, from a provided plurality of secondary data object image representations, in dependence upon the trained neural network system, and storing the image representations from the selected subset of secondary data object image representations in a tangible machine readable memory for use in a data object creation and recommendation system.

10. 发明申请

US20180114118A1 Alife Machine Learning System and Method 审中-公开
公开(公告)号：US20180114118A1
公开(公告)日：2018-04-26
申请号：US15851294
申请日：2017-12-21
申请人： SENTIENT TECHNOLOGIES (BARBADOS) LIMITED
发明人： Babak Hodjat , Hormoz Shahrzad
IPC分类号： G06N3/12 , G06F17/30 , G06F15/18
CPC分类号： G06N3/126 , A63F13/45 , G06F9/45516 , G06F16/00 , G06F16/2465 , G06F2216/03 , G06N20/00
摘要： Roughly described, a problem solving platform distributes the solving of the problem over a evolvable individuals, each of which also evolves its own pool of actors. The actors have the ability to contribute collaboratively to a solution at the level of the individual, instead of each actor being a candidate for the full solution. Populations evolve both at the level of the individual and at the level of actors within an individual. In an embodiment, an individual defines parameters according to which its population of actors can evolve. The individual is fixed prior to deployment to a production environment, but its actors can continue to evolve and adapt while operating in the production environment. Thus a goal of the evolutionary process at the level of individuals is to find populations of actors that can sustain themselves and survive, solving a dynamic problem for a given domain as a consequence.

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