-
21.发明授权公开(公告)号：US09824683B2
公开(公告)日：2017-11-21
申请号：US14977674
申请日：2015-12-22
Applicant: International Business Machines Corporation
Inventor： Xiaodong Cui , Vaibhava Goel , Brian E. D. Kingsbury
IPC: G10L15/00 , G10L15/06 , G10L21/0272 , G10L15/16 , G10L15/02
CPC classification number: G10L15/063 , G10L15/02 , G10L15/16 , G10L21/0272
Abstract: A method of augmenting training data includes converting a feature sequence of a source speaker determined from a plurality of utterances within a transcript to a feature sequence of a target speaker under the same transcript, training a speaker-dependent acoustic model for the target speaker for corresponding speaker-specific acoustic characteristics, estimating a mapping function between the feature sequence of the source speaker and the speaker-dependent acoustic model of the target speaker, and mapping each utterance from each speaker in a training set using the mapping function to multiple selected target speakers in the training set.
-
22.发明申请公开(公告)号：US20170200446A1
公开(公告)日：2017-07-13
申请号：US14977674
申请日：2015-12-22
Applicant: International Business Machines Corporation
Inventor： Xiaodong Cui , Vaibhava Goel , Brian E. D. Kingsbury
IPC: G10L15/06 , G10L15/16 , G10L15/02 , G10L21/0272
CPC classification number: G10L15/063 , G10L15/02 , G10L15/16 , G10L21/0272
Abstract: A method of augmenting training data includes converting a feature sequence of a source speaker determined from a plurality of utterances within a transcript to a feature sequence of a target speaker under the same transcript, training a speaker-dependent acoustic model for the target speaker for corresponding speaker-specific acoustic characteristics, estimating a mapping function between the feature sequence of the source speaker and the speaker-dependent acoustic model of the target speaker, and mapping each utterance from each speaker in a training set using the mapping function to multiple selected target speakers in the training set.
-
公开(公告)号：US20250005324A1
公开(公告)日：2025-01-02
申请号：US18217081
申请日：2023-06-30
Inventor： Siliang Zeng , Songtao Lu , Xiaodong Cui , Mark S. Squillante , Lior Horesh , Brian E. D. Kingsbury , Mingyi Hong
IPC: G06N3/045
Abstract: A computer-implemented method of decentralized multi-agent learning for use in a system having a plurality of intelligent agents each having a personal portion and a shared portion, is provided. The method includes iteratively, until each of a personal goal and a network goal are optimized: determining a feedback associated with an action relative to a personal goal and a degree of similarity relative to a shared goal; adjusting a policy based on the feedback to gain a superior feedback from a next action; broadcasting the shared policy; receiving the at least one of the one or more other intelligent agents' shared policy; generating a combined policy by combining the personal policy and the at least one of the one or more other intelligent agents' shared policy; estimating, using the combined policy, a network value function; and conducting the next action in accordance with the combined policy.
-
公开(公告)号：US12148419B2
公开(公告)日：2024-11-19
申请号：US17549006
申请日：2021-12-13
Applicant: International Business Machines Corporation
Inventor： Xiaodong Cui , Brian E. D. Kingsbury , George Andrei Saon , David Haws , Zoltan Tueske
Abstract: Mechanisms are provided for performing machine learning training of a computer model. A perturbation generator generates a modified training data comprising perturbations injected into original training data, where the perturbations cause a data corruption of the original training data. The modified training data is input into a prediction network of the computer model and processing the modified training data through the prediction network to generate a prediction output. Machine learning training is executed of the prediction network based on the prediction output and the original training data to generate a trained prediction network of a trained computer model. The trained computer model is deployed to an artificial intelligence computing system for performance of an inference operation.
-
25.发明公开公开(公告)号：US20230205843A1
公开(公告)日：2023-06-29
申请号：US18176765
申请日：2023-03-01
Applicant: International Business Machines Corporation
Inventor： Xiaodong Cui , Wei Zhang , Mingrui Liu , Abdullah Kayi , Youssef Mroueh , Alper Buyuktosunoglu
IPC: G06F18/214 , G06F15/173 , G06N20/00 , G06N3/08 , G06F18/20
CPC classification number: G06F18/214 , G06F15/17375 , G06F18/285 , G06N3/08 , G06N20/00
Abstract: Systems, computer-implemented methods, and computer program products to facilitate updating, such as averaging and/or training, of one or more statistical sets are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can include a computing component that averages a statistical set, provided by the system, with an additional statistical set, that is compatible with the statistical set, to compute an averaged statistical set, where the additional statistical set is obtained from a selected additional system of a plurality of additional systems. The computer executable components also can include a selecting component that selects the selected additional system according to a randomization pattern.
-
Patent Agency Ranking
公开(公告)号：US11669780B2
公开(公告)日：2023-06-06
申请号：US16675555
申请日：2019-11-06
Applicant: International Business Machines Corporation
Inventor： Li Zhang , Wei Zhang , Xiaodong Cui
IPC: G06N20/20
CPC classification number: G06N20/20
Abstract: Building machine learning models by receiving, a plurality of training process scores associated with the model parameter lists, determining, a best model parameter list according to the training process scores, determining a descendant model parameter list according to the best model parameter list, wherein the descendant parameter list comprises a portion of the best model parameter list, distributing the descendant model parameter list, conducting a model training process according to the descendant model parameter list, determining a training process score according to the descendant model parameter list, and sending the training process score for the descendant model parameter list.
-
公开(公告)号：US11651293B2
公开(公告)日：2023-05-16
申请号：US16935246
申请日：2020-07-22
Applicant: International Business Machines Corporation
Inventor： Wei Zhang , Xiaodong Cui , Abdullah Kayi , Alper Buyuktosunoglu
Abstract: Embodiments of a method are disclosed. The method includes performing a batch of decentralized deep learning training for a machine learning model in coordination with multiple local homogenous learners on a deep learning training compute node, and in coordination with multiple super learners on corresponding deep learning training compute nodes. The method also includes exchanging communications with the super learners in accordance with an asynchronous decentralized parallel stochastic gradient descent (ADPSGD) protocol. The communications are associated with the batch of deep learning training.
-
公开(公告)号：US20220383185A1
公开(公告)日：2022-12-01
申请号：US17334889
申请日：2021-05-31
Applicant: International Business Machines Corporation
Inventor： Yada Zhu , Wei Zhang , Guangnan Ye , Xiaodong Cui
Abstract: Hessian matrix-free sample-based techniques for model explanations that are faithful to the model are provided. In one aspect, a method for explaining a machine learning model {circumflex over (θ)} (e.g., for natural language processing) is provided. The method includes: training the machine learning model {circumflex over (θ)} with training data D; obtaining a decision of the machine learning model {circumflex over (θ)}; and explaining the decision of the machine learning model {circumflex over (θ)} using training examples from the training data D.
-
29.发明申请公开(公告)号：US20220374747A1
公开(公告)日：2022-11-24
申请号：US17314450
申请日：2021-05-07
Applicant: International Business Machines Corporation
Inventor： Wei Zhang , Xiaodong Cui , Xin Wang , Zhaonan Sun
IPC: G06N7/00
Abstract: Systems, computer-implemented methods, and/or computer program products to facilitate updating, such as averaging and/or training, of one or more statistical sets are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can include a computing component that updates a first statistical set with an additional statistical set from an additional system. The additional statistical set can have been generated from a parent statistical set that is based on underlying data. To update the first statistical set, the additional statistical set can be obtained by the system without obtaining the parent statistical set and without obtaining the underlying data. According to an embodiment, the first statistical set can be a model parameter set generated from a first parent statistical set that is an analytical model.
-
公开(公告)号：US20220027796A1
公开(公告)日：2022-01-27
申请号：US16935246
申请日：2020-07-22
Applicant: International Business Machines Corporation
Inventor： Wei Zhang , Xiaodong Cui , Abdullah Kayi , Alper Buyuktosunoglu
Abstract: Embodiments of a method are disclosed. The method includes performing a batch of decentralized deep learning training for a machine learning model in coordination with multiple local homogenous learners on a deep learning training compute node, and in coordination with multiple super learners on corresponding deep learning training compute nodes. The method also includes exchanging communications with the super learners in accordance with an asynchronous decentralized parallel stochastic gradient descent (ADPSGD) protocol. The communications are associated with the batch of deep learning training.
-
-
-
-
-
-
-
-
-
Search Results
45
records
(took 0.023 seconds)
