JP2023058454A5 - - Google Patents

Info

Publication number
JP2023058454A5
JP2023058454A5 JP2022163230A JP2022163230A JP2023058454A5 JP 2023058454 A5 JP2023058454 A5 JP 2023058454A5 JP 2022163230 A JP2022163230 A JP 2022163230A JP 2022163230 A JP2022163230 A JP 2022163230A JP 2023058454 A5 JP2023058454 A5 JP 2023058454A5
Authority
JP
Japan
Prior art keywords
dataset
feature
module
bias
metric
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
JP2022163230A
Other languages
English (en)
Japanese (ja)
Other versions
JP2023058454A (ja
Filing date
Publication date
Priority claimed from US17/450,694 external-priority patent/US12443676B2/en
Application filed filed Critical
Publication of JP2023058454A publication Critical patent/JP2023058454A/ja
Publication of JP2023058454A5 publication Critical patent/JP2023058454A5/ja
Pending legal-status Critical Current

Links

JP2022163230A 2021-10-13 2022-10-11 機械学習モジュールのバックグラウンドのバイアスの制御のためのコンピュータ実装方法、コンピュータプログラム製品およびコンピュータシステム（機械学習モジュールのバックグラウンドのバイアスの制御） Pending JP2023058454A (ja)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US17/450,694 2021-10-13
US17/450,694 US12443676B2 (en) 2021-10-13 2021-10-13 Controlling a bias of a machine learning module background

Publications (2)

Publication Number Publication Date
JP2023058454A JP2023058454A (ja) 2023-04-25
JP2023058454A5 true JP2023058454A5 (https=) 2026-01-19

Family

ID=85797029

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2022163230A Pending JP2023058454A (ja) 2021-10-13 2022-10-11 機械学習モジュールのバックグラウンドのバイアスの制御のためのコンピュータ実装方法、コンピュータプログラム製品およびコンピュータシステム（機械学習モジュールのバックグラウンドのバイアスの制御）

Country Status (2)

Country Link
US (1) US12443676B2 (https=)
JP (1) JP2023058454A (https=)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20220391683A1 (en) * 2021-06-07 2022-12-08 International Business Machines Corporation Bias reduction during artifical intelligence module training
US12481919B2 (en) * 2022-04-25 2025-11-25 Business Objects Software Ltd. Discrimination likelihood estimate for trained machine learning model

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020159641A1 (en) * 2001-03-14 2002-10-31 Whitney Paul D. Directed dynamic data analysis
EP3256964A4 (en) * 2015-02-13 2018-10-17 National ICT Australia Limited Learning from distributed data
US20200372304A1 (en) 2018-07-31 2020-11-26 Microsoft Technology Licensing, Llc Quantifying bias in machine learning models
CA3134043C (en) 2019-03-18 2024-10-29 Zestfinance, Inc. MODEL EQUITY SYSTEMS AND METHODS
US20200320428A1 (en) 2019-04-08 2020-10-08 International Business Machines Corporation Fairness improvement through reinforcement learning
US11775863B2 (en) 2019-05-22 2023-10-03 Oracle International Corporation Enforcing fairness on unlabeled data to improve modeling performance

Similar Documents

Publication Publication Date Title
US10445657B2 (en) General framework for cross-validation of machine learning algorithms using SQL on distributed systems
US8914802B2 (en) Feedback-driven tuning for efficient parallel execution
US20050267866A1 (en) Determining validity ranges of query plans based on suboptimality
JP2023058454A5 (https=)
US10599652B2 (en) Database query time estimator
JP2025514974A5 (https=)
CN115640888B (zh) 一种递减函数嵌入式门限序列网络的产量预测方法
CN110109811B (zh) 一种面向gpu计算性能问题的溯源方法
JP2005049922A (ja) ジョブ実行計画の評価システム
CN103268254B (zh) 控制依赖死锁检测方法和装置
CN115409541B (zh) 基于数据血缘的卷烟品牌数据处理方法
JP2012221254A (ja) 並列処理最適化装置及びシミュレーションプログラム
JP2004110470A (ja) 最適設計計算装置及びそのプログラム記憶媒体
JPWO2024180789A5 (https=)
CN114185970A (zh) 一种基于独立概率完全加权的并行关联规则挖掘方法
JPWO2024189883A5 (https=)
Abe et al. Analyzing business processes by automatically detecting kpi thresholds
JP5326442B2 (ja) 統計量推定装置、統計量推定プログラム、統計量推定方法
US12223395B2 (en) Circuit cutting taking into account transpilation error
CN106202486B (zh) 异构数据集基于mic的字段值优先连接方法
Qvick Parallel construction of variable length Markov models for DNA sequences
CN114648228B (zh) 一种业务执行效率的评估方法、装置及设备
US12373019B2 (en) Recommendation framework of model and hardware for energy-efficient machine learning workloads
CN112650770B (zh) 基于query workload分析的MySQL参数推荐方法
KR20260045582A (ko) 하이퍼파라미터 설정 방법 및 그 방법을 이용한 장치