-
公开(公告)号：US11997237B1
公开(公告)日：2024-05-28
申请号：US17378236
申请日：2021-07-16
申请人： Daniel Lydick
发明人： Daniel Lydick
IPC分类号： G06V30/414 , G06T1/00 , H04N1/00 , H04N9/31
CPC分类号： H04N1/00816 , G06T1/0007 , G06V30/414 , H04N1/00005 , H04N1/00034 , H04N1/00822 , H04N1/00824 , H04N1/00827 , H04N9/3194
摘要： Embodiments include a method, computer-implemented method, and apparatus to provide local soft-copy access, local hard-copy access, remote or web-based access to information, text, and content articulated in a scroll. Indices are created and then utilized to locate and access text within the scroll. In addition, rulers are employed with the indices to locate indicia within the scroll, including accommodating scrolls of different archetypes.
-
公开(公告)号：US11645515B2
公开(公告)日：2023-05-09
申请号：US16571323
申请日：2019-09-16
IPC分类号： G06G7/00 , G06N3/08 , G06N20/00 , G06F18/23 , G06F18/24 , G06V10/762 , G06V10/771 , G06V10/776
CPC分类号： G06N3/08 , G06F18/23 , G06F18/24 , G06N20/00 , G06V10/762 , G06V10/771 , G06V10/776
摘要： Embodiments relate to a system, program product, and method for automatically determining which activation data points in a neural model have been poisoned to erroneously indicate association with a particular label or labels. A neural network is trained using potentially poisoned training data. Each of the training data points is classified using the network to retain the activations of the last hidden layer, and segment those activations by the label of corresponding training data. Clustering is applied to the retained activations of each segment, and a cluster assessment is conducted for each cluster associated with each label to distinguish clusters with potentially poisoned activations from clusters populated with legitimate activations. The assessment includes executing a set of analyses and integrating the results of the analyses into a determination as to whether a training data set is poisonous based on determining if resultant activation clusters are poisoned.
-
公开(公告)号：US11616186B1
公开(公告)日：2023-03-28
申请号：US17359729
申请日：2021-06-28
发明人： Joseph Birmingham
摘要： Embodiments relate to systems designed for thermal transfer augmentation and thermionic energy harvesting. Thermionic energy harvesters are configured to supply electricity for applications such as electronics, communications, and other electrical devices. Thermal transfer may be used for a variety of heating/cooling and power generation/heat recovery systems, such as, refrigeration, air conditioning, electronics cooling, industrial temperature control, waste heat recovery, off-grid and mobile refrigeration, and cold storage.
-
公开(公告)号：US11588625B2
公开(公告)日：2023-02-21
申请号：US17211237
申请日：2021-03-24
发明人： Chad DeLuca , Daniel Gruhl , Linda Kato , Cartic Ramakrishnan , Chris Kau , Alfredo Alba
摘要： Embodiments relate to a system, program product, and method for use with a physical computing device to process a data access request. The requested data is encrypted with two keys, including a physical device authentication key and a transient key. Access to the data requires authentication on both the device level and situational level. Device situational data is monitored, which includes selectively enabling access to the requested data and de-activation of the transient key in response to a change in the monitored situational data. The transient key de-activation removes access to the requested data.
-
公开(公告)号：US11538236B2
公开(公告)日：2022-12-27
申请号：US16571318
申请日：2019-09-16
IPC分类号： G06V10/774 , G06K9/62 , G06N3/04 , G06N3/08 , G06V10/764 , G06V10/762
摘要： Embodiments relate to a system, program product, and method for processing an untrusted data set to automatically determine which data points there are poisonous. A neural network is trained network using potentially poisoned training data. Each of the training data points is classified using the network to retain the activations of at least one hidden layer, and segment those activations by the label of corresponding training data. Clustering is applied to the retained activations of each segment, and a clustering assessment is conducted to remove an identified cluster from the data set, form a new training set, and train a second neural model with the new training set. The removed cluster and corresponding data are applied to the trained second neural model to analyze and classify data in the removed cluster as either legitimate or poisonous.
-
公开(公告)号：US11537433B2
公开(公告)日：2022-12-27
申请号：US17161988
申请日：2021-01-29
申请人： Kyndryl, Inc.
发明人： Sai Zeng , Braulio Gabriel Dumba , Matthew Staffelbach , Liang Liu , Emrah Zarifoglu , Umar Mohamed Iyoob , Manish Mahesh Modh
摘要： A system, computer program product, and method to deriving a cost model and dynamic adjustment of the derived model responsive to dynamic modification of one or more of the resources in a hybrid shared resource environment. Resources and corresponding configuration information are collected while monitoring runtime utilization of resource performance. As changes to the resources are discovered, the changes are subject to an assessment. A hybrid cost model is derived and configured to account for the one or more resources. The derived hybrid cost model is leveraged to conduct a multi-dimensional resource evaluation of the assessed changed configuration information. Responsive to the multi-dimensional evaluation, a generated resource utilization optimization of the one or more resources is selectively implemented.
-
公开(公告)号：US11488064B2
公开(公告)日：2022-11-01
申请号：US16834463
申请日：2020-03-30
发明人： Muhammed Fatih Bulut , Jinho Hwang , Ali Kanso , Shripad Nadgowda
摘要： Embodiments relate to a computer system, computer program product, and computer-implemented method to train a machine learning (ML) model using artificial intelligence to learn an association between (regulatory) compliance requirements and features of micro-service training datasets. The trained ML model is leveraged to determine the compliance requirements of a micro-service requiring classification. In an exemplary embodiment, once the micro-service has been classified with respect to applicable compliance requirements, the classified micro-service may be used as an additional micro-service training dataset to further train the ML model and thereby improve its performance.
-
公开(公告)号：US11443216B2
公开(公告)日：2022-09-13
申请号：US16262479
申请日：2019-01-30
摘要： A system, computer program product, and method are provided to conduct gap probability mapping to predict presence and location of one or more gaps in a corpus. A probabilistic model is formed to represent inter-corpora associations of objects, which the model leverages to process query submissions. As queries are received and processed, the model creates an adjustment. Subject to evaluation, confidence of the adjustment is evaluated, and a response correlated to the confidence is returned.
-
公开(公告)号：US11429789B2
公开(公告)日：2022-08-30
申请号：US16439216
申请日：2019-06-12
IPC分类号： G06F40/20 , G06F40/284 , H04L51/02 , G06F16/9032 , G06F40/56 , G06F40/205
摘要： Embodiments relate to an intelligent computer platform to identify and evaluate candidate passage response data in natural language form. Natural language processing is applied to analyze a passage against one or more input tokens to identify matching content. A structure representing the analyzed passage is populated with matching input and passage tokens. A first count of matching token entries and a second count of evaluated token entries are determined and qualified by closeness criteria. An alignment of the passage to a candidate question is calculated, including assessing a ratio of the first and second counts as a confidence value. Matching passage data is returned from the passage with the confidence value.
-
公开(公告)号：US11429434B2
公开(公告)日：2022-08-30
申请号：US16724613
申请日：2019-12-23
发明人： Liana Fong , Seetharami R. Seelam , Ganesh Venkataraman , Debashish Saha , Punleuk Oum , Archit Verma , Prabhat Maddikunta Reddy
摘要： Embodiments relate to a system, program product, and method for supporting elastic execution of a machine learning (ML) workload using application based profiling. A joint profile comprised of both ML application execution and resource usage data is generated. One or more feature(s) and signature(s) from the joint profile are identified, and a ML execution model for ML application execution and resource usage is built. The ML execution model leverages the feature(s) and signature(s) and is applied to provide one or more directives to subsequent application execution. The application of the ML execution model supports and enables the ML execution to elastically allocate and request one or more resources from a resource management component, with the elastic allocation supporting application execution.
-
-
-
-
-
-
-
-
-
搜索结果
749 条记录 (耗时 0.029 秒)
