-
公开(公告)号：US12093245B2
公开(公告)日：2024-09-17
申请号：US16852312
申请日：2020-04-17
IPC分类号： G06N20/00 , G06F16/23 , G06F16/901 , G06Q20/40
CPC分类号： G06F16/2379 , G06F16/9024 , G06N20/00 , G06Q20/4016
摘要： A method for improving computing efficiency of a computing device for temporal directed cycle detection in a transaction graph includes preparing the transaction graph based on a plurality of transactions, the transaction graph including nodes indicating transaction origination points and transaction destination points, and edges indicating interactions between the nodes. Irrelevant nodes in the transaction graph are identified and pruned to provide a pruned, preprocessed transaction graph which can be partitioning into sections, where each section includes selected nodes that are linked to other linked nodes therein. Each of the sections having non-cyclic nodes can be trimmed prior to performing cycle detection on the resulting pruned transaction graph. Postprocessing pruning can be performed to further reduce the number of detected cycles that may be of interest to a particular application, such as in anti-money laundering.
-
公开(公告)号：US20230056772A1
公开(公告)日：2023-02-23
申请号：US17408944
申请日：2021-08-23
发明人： Yada Zhu , Wei Zhang , Guangnan Ye , Xiaodong Cui
摘要： A neural network to predict a future indicator of a given entity can be trained based on historical earnings call data and historical market data. An earnings call transcript can be received, from which to predict the future indicator. Preprocessing can be performed using a natural language processing (NLP) technique to select candidate sentences from the earnings call transcript. For a candidate sentence in the candidate sentences, and using the trained neural network, a sentence gradient can be determined, which is indicative of sensitivity of the trained neural network to the candidate sentence. Based on the determined sentence gradient associated with each of the candidate sentences, an explanation of the trained neural network's predicted future indicator can be provided.
-
公开(公告)号：US20220383185A1
公开(公告)日：2022-12-01
申请号：US17334889
申请日：2021-05-31
发明人： Yada Zhu , Wei Zhang , Guangnan Ye , Xiaodong Cui
摘要： 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.
-
公开(公告)号：US11093832B2
公开(公告)日：2021-08-17
申请号：US15788523
申请日：2017-10-19
发明人： Chun-Fu Chen , Jui-Hsin Lai , Ching-Yung Lin , Guangnan Ye , Ruichi Yu
摘要： Method and apparatus for optimizing a convolutional neural network (CNN). A respective measure of importance is calculated for each of a plurality of elements within a CNN. A first one of the measures of importance is calculated by back propagating a second one of the measures of importance through the CNN. One or more of the plurality of elements is pruned from the CNN, based on the calculated measures of importance.
-
公开(公告)号：US20220358594A1
公开(公告)日：2022-11-10
申请号：US17315764
申请日：2021-05-10
发明人： Yada Zhu , Wei Zhang , Xiaodong Cui , Guangnan Ye
摘要： A machine learning model can be trained to predict one or more financial indicators using earnings call transcripts augmented with counterfactual information. Using faithful gradient-based method, prediction results with respect to a particular counterfactual information can be explained. Based on the explanation, the counterfactual information determined to have most impact on prediction results can be selected for updating the machine learning model.
-
公开(公告)号：US20210326332A1
公开(公告)日：2021-10-21
申请号：US16852312
申请日：2020-04-17
IPC分类号： G06F16/23 , G06F16/901 , G06N20/00 , G06Q20/40
摘要： A method for improving computing efficiency of a computing device for temporal directed cycle detection in a transaction graph includes preparing the transaction graph based on a plurality of transactions, the transaction graph including nodes indicating transaction origination points and transaction destination points, and edges indicating interactions between the nodes. Irrelevant nodes in the transaction graph are identified and pruned to provide a pruned, preprocessed transaction graph which can be partitioning into sections, where each section includes selected nodes that are linked to other linked nodes therein. Each of the sections having non-cyclic nodes can be trimmed prior to performing cycle detection on the resulting pruned transaction graph. Postprocessing pruning can be performed to further reduce the number of detected cycles that may be of interest to a particular application, such as in anti-money laundering.
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.015 秒)
