-
公开(公告)号：US11436444B1
公开(公告)日：2022-09-06
申请号：US17557298
申请日：2021-12-21
申请人： SAS Institute Inc.
发明人： Xinmin Wu , Xin Jiang Hunt
摘要： A computing device trains a fair machine learning model. A prediction model is trained to predict a target value. For a number of iterations, a weight vector is computed using the bound value based on fairness constraints defined for a fairness measure type; a weight value is assigned to each observation vector based on the target value and a sensitive attribute value; the prediction model is trained with each weighted observation vector to predict the target value; and a conditional moments vector is computed based on the fairness constraints and the target and sensitive attribute values. Conditional moments difference values are computed. When the conditional moments difference values indicate to adjust the bound value, the bound value is updated and the process is repeated with the bound value replaced with the updated bound value until the conditional moments difference values indicate no further adjustment of the bound value is needed.
-
公开(公告)号：US20220114449A1
公开(公告)日：2022-04-14
申请号：US17499972
申请日：2021-10-13
申请人： SAS Institute Inc.
发明人： Xinmin Wu , Yingjian Wang , Xiangqian Hu
摘要： A computing device trains a neural network machine learning model. A forward propagation of a first neural network is executed. A backward propagation of the first neural network is executed from a last layer to a last convolution layer to compute a gradient vector. A discriminative localization map is computed for each observation vector with the computed gradient vector using a discriminative localization map function. An activation threshold value is selected for each observation vector from at least two different values based on a prediction error of the first neural network. A biased feature map is computed for each observation vector based on the activation threshold value selected for each observation vector. A masked observation vector is computed for each observation vector using the biased feature map. A forward and a backward propagation of a second neural network is executed a predefined number of iterations using the masked observation vector.
-
3.发明申请公开(公告)号：US20190129919A1
公开(公告)日：2019-05-02
申请号：US16140931
申请日：2018-09-25
申请人： SAS Institute Inc.
发明人： Xinmin Wu , Xiangqian Hu , Tao Wang , Xunlei Wu
IPC分类号： G06F17/18
摘要： A computing device computes a quantile value. A maximum value and a minimum value are computed for unsorted variable values to compute an upper bin value and a lower bin value for each bin of a plurality of bins. A frequency counter is computed for each bin by reading the unsorted variable values a second time. A bin number and a cumulative rank value are computed for a quantile. When an estimated memory usage value exceeds a predefined memory size constraint value, a subset of the plurality of bins are split into a plurality of bins, the frequency counter is recomputed for each bin, and the bin number and the cumulative rank value are recomputed. Frequency data is computed using the frequency counters. The quantile value is computed using the frequency data and the cumulative rank value for the quantile and output.
-
公开(公告)号：US09619848B2
公开(公告)日：2017-04-11
申请号：US14270589
申请日：2014-05-06
申请人： SAS Institute Inc.
发明人： Arnulfo D. de Castro , Glenn Lampley , Xinmin Wu , Greg Link
CPC分类号： G06Q50/06 , H02J3/12 , H02J3/1821 , H02J2003/003 , H02J2003/007 , Y02E40/30 , Y02E40/76 , Y02E60/76 , Y04S10/54 , Y04S10/545 , Y04S40/22
摘要： Techniques to determine settings for an electrical distribution network are described. Some embodiments are particularly directed to techniques to determine settings for an electrical distribution network using power flow heuristics. In one embodiment, for example, an apparatus may comprise a model reception component, a forecast component, and an optimization component. The model reception component may be operative to receive a model of an electrical distribution network having multiple capacitor banks and multiple voltage regulators, each of the multiple capacitor banks represented in the model by a model capacitor bank, each of the multiple voltage regulators represented in the model by a model voltage regulator, the electrical distribution network having a radial layout in which power flows from a source to multiple nodes in which each node is associated with one voltage regulator. The forecast reception component may be operative to receive a forecast for demand on the electrical distribution network. The optimization component may be operative to receive the model capacitor banks and model voltage regulators and determine one or more settings for the multiple capacitor banks and multiple voltage regulators that allow for providing power within predetermined limits while reducing power loss as compared to a power loss of the existing settings or reducing power usage as compared to a power usage of the existing settings, the one or more settings for the multiple voltage regulators determined according to a heuristic in which potential settings are iteratively determined for each of the model voltage regulators based on a least squares model of load flow analysis. Other embodiments are described and claimed.
-
公开(公告)号：US11922311B2
公开(公告)日：2024-03-05
申请号：US18208455
申请日：2023-06-12
申请人： SAS Institute Inc.
摘要： A computing device trains a fair prediction model. A prediction model is trained and executed with observation vectors. A weight value is computed for each observation vector based on whether the predicted target variable value of a respective observation vector of the plurality of observation vectors has a predefined target event value. An observation vector is relabeled based on the computed weight value. The prediction model is retrained with each observation vector weighted by a respective computed weight value and with the target variable value of any observation vector that was relabeled. The retrained prediction model is executed. A conditional moments matrix is computed. A constraint violation matrix is computed. Computing the weight value through computing the constraint violation matrix is repeated until a stop criterion indicates retraining of the prediction model is complete. The retrained prediction model is output.
-
公开(公告)号：US20230359890A1
公开(公告)日：2023-11-09
申请号：US18208455
申请日：2023-06-12
申请人： SAS Institute Inc.
IPC分类号： G06N20/00
CPC分类号： G06N20/00
摘要： A computing device trains a fair prediction model. A prediction model is trained and executed with observation vectors. A weight value is computed for each observation vector based on whether the predicted target variable value of a respective observation vector of the plurality of observation vectors has a predefined target event value. An observation vector is relabeled based on the computed weight value. The prediction model is retrained with each observation vector weighted by a respective computed weight value and with the target variable value of any observation vector that was relabeled. The retrained prediction model is executed. A conditional moments matrix is computed. A constraint violation matrix is computed. Computing the weight value through computing the constraint violation matrix is repeated until a stop criterion indicates retraining of the prediction model is complete. The retrained prediction model is output.
-
公开(公告)号：US11531845B1
公开(公告)日：2022-12-20
申请号：US17837444
申请日：2022-06-10
申请人： SAS Institute Inc.
发明人： Xin Jiang Hunt , Xinmin Wu , Ralph Walter Abbey
摘要： A computing device trains a fair machine learning model. A prediction model is trained to predict a target value. For a number of iterations, a weight vector is computed using the bound value based on fairness constraints defined for a fairness measure type; a weight value is assigned to each observation vector based on the target value and a sensitive attribute value; the prediction model is trained with each weighted observation vector to predict the target value; and a conditional moments vector is computed based on the fairness constraints and the target and sensitive attribute values. Conditional moments difference values are computed. When the conditional moments difference values indicate to adjust the bound value, the bound value is updated and the process is repeated with the bound value replaced with the updated bound value until the conditional moments difference values indicate no further adjustment of the bound value is needed.
-
8.发明公开公开(公告)号：US20240193416A1
公开(公告)日：2024-06-13
申请号：US18444906
申请日：2024-02-19
申请人： SAS Institute Inc.
IPC分类号： G06N5/022
CPC分类号： G06N5/022
摘要： A computing device trains a fair prediction model while defining an optimal event cutoff value. (A) A prediction model is trained with observation vectors. (B) The prediction model is executed to define a predicted target variable value and a probability associated with an accuracy of the predicted target variable value. (C) A conditional moments matrix is computed based on fairness constraints, the predicted target variable value, and the sensitive attribute variable value of each observation vector. The predicted target variable value has a predefined target event value only when the probability is greater than a predefined event cutoff value. (D) (A) through (C) are repeated. (E) An updated value is computed for the predefined event cutoff value. (F) (A) through (E) are repeated. An optimal event cutoff value is defined from the predefined event cutoff values used when repeating (A) through (E). The optimal value and prediction model are output.
-
公开(公告)号：US11790036B2
公开(公告)日：2023-10-17
申请号：US18051906
申请日：2022-11-02
申请人： SAS Institute Inc.
发明人： Xinmin Wu , Xin Jiang Hunt , Ralph Walter Abbey
摘要： A computing device trains a fair machine learning model. A predicted target variable is defined using a trained prediction model. The prediction model is trained with weighted observation vectors. The predicted target variable is updated using the prediction model trained with weighted observation vectors. A true conditional moments matrix and a false conditional moments matrix are computed. The training and updating with weighted observation vectors are repeated until a number of iterations is performed. When a computed conditional moments matrix indicates to adjust a bound value, the bound value is updated based on an upper bound value or a lower bound value, and the repeated training and updating with weighted observation vectors is repeated with the bound value replaced with the updated bound value until the conditional moments matrix indicates no further adjustment of the bound value is needed. A fair prediction model is trained with the updated bound value.
-
公开(公告)号：US20230205839A1
公开(公告)日：2023-06-29
申请号：US18051906
申请日：2022-11-02
申请人： SAS Institute Inc.
发明人： Xinmin Wu , Xin Jiang Hunt , Ralph Walter Abbey
摘要： A computing device trains a fair machine learning model. A predicted target variable is defined using a trained prediction model. The prediction model is trained with weighted observation vectors. The predicted target variable is updated using the prediction model trained with weighted observation vectors. A true conditional moments matrix and a false conditional moments matrix are computed. The training and updating with weighted observation vectors are repeated until a number of iterations is performed. When a computed conditional moments matrix indicates to adjust a bound value, the bound value is updated based on an upper bound value or a lower bound value, and the repeated training and updating with weighted observation vectors is repeated with the bound value replaced with the updated bound value until the conditional moments matrix indicates no further adjustment of the bound value is needed. A fair prediction model is trained with the updated bound value.
-
-
-
-
-
-
-
-
-
搜索结果
19 条记录 (耗时 0.017 秒)
