CN118140238A - 用于经训练的模型偏差评价的技术 - Google Patents

用于经训练的模型偏差评价的技术 Download PDF

Info

Publication number
CN118140238A
CN118140238A CN202280070137.7A CN202280070137A CN118140238A CN 118140238 A CN118140238 A CN 118140238A CN 202280070137 A CN202280070137 A CN 202280070137A CN 118140238 A CN118140238 A CN 118140238A
Authority
CN
China
Prior art keywords
bias
model
data
trained
trained model
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
CN202280070137.7A
Other languages
English (en)
Chinese (zh)
Inventor
H·B·桑卡拉纳拉亚南
S·雷扎
A·卡蒂亚尔
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Oracle International Corp
Original Assignee
Oracle International Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Oracle International Corp filed Critical Oracle International Corp
Publication of CN118140238A publication Critical patent/CN118140238A/zh
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/088—Non-supervised learning, e.g. competitive learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0475—Generative networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • G06N5/022—Knowledge engineering; Knowledge acquisition

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Medical Informatics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Image Analysis (AREA)
CN202280070137.7A 2021-10-22 2022-08-17 用于经训练的模型偏差评价的技术 Pending CN118140238A (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US17/508,734 US20230131834A1 (en) 2021-10-22 2021-10-22 Techniques for trained model bias assessment
US17/508,734 2021-10-22
PCT/US2022/075052 WO2023069799A1 (en) 2021-10-22 2022-08-16 Techniques for trained model bias assessment

Publications (1)

Publication Number Publication Date
CN118140238A true CN118140238A (zh) 2024-06-04

Family

ID=83271693

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202280070137.7A Pending CN118140238A (zh) 2021-10-22 2022-08-17 用于经训练的模型偏差评价的技术

Country Status (5)

Country Link
US (1) US20230131834A1 (https=)
EP (1) EP4420051A1 (https=)
JP (1) JP2024540956A (https=)
CN (1) CN118140238A (https=)
WO (1) WO2023069799A1 (https=)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12353473B2 (en) * 2022-07-07 2025-07-08 Hewlett Packard Enterprise Development Lp Image data bias detection with explainability in machine learning
US20240111995A1 (en) * 2022-10-04 2024-04-04 International Business Machines Corporation Predicting future possibility of bias in an artificial intelligence model
US20250148657A1 (en) * 2023-11-02 2025-05-08 Sony Group Corporation Dataset-level societal bias mitigation with text-to-image model

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11625647B2 (en) * 2018-05-25 2023-04-11 Todd Marlin Methods and systems for facilitating analysis of a model
US20220114399A1 (en) * 2020-10-08 2022-04-14 Royal Bank Of Canada System and method for machine learning fairness testing

Also Published As

Publication number Publication date
WO2023069799A8 (en) 2024-04-18
JP2024540956A (ja) 2024-11-06
US20230131834A1 (en) 2023-04-27
EP4420051A1 (en) 2024-08-28
WO2023069799A1 (en) 2023-04-27

Similar Documents

Publication Publication Date Title
US12566982B2 (en) Chatbot for defining a machine learning (ML) solution
EP4028875B1 (en) Machine learning infrastructure techniques
CN114616560B (zh) 用于机器学习（ml）的自适应和上下文感知自动化服务组成的技术
US20220351132A1 (en) Systems and methods for intelligent field matching and anomaly detection
US20210081848A1 (en) Techniques for adaptive pipelining composition for machine learning (ml)
US12242332B2 (en) Identifying root cause anomalies in time series
US11687568B2 (en) Data catalog system for generating synthetic datasets
CN116762315A (zh) 利用人工智能自动修复安全问题的技术
CN118140238A (zh) 用于经训练的模型偏差评价的技术
US12299005B2 (en) Model mining and recommendation engine with simulation interfaces
US11449773B2 (en) Enhanced similarity detection between data sets with unknown prior features using machine-learning
US20250077534A1 (en) Techniques for detecting anomalous data points in time series data
US20240112065A1 (en) Meta-learning operation research optimization
US20240362517A1 (en) Univariate series truncation policy using changepoint detection
US20230267478A1 (en) Event attribution for estimating down stream impact
US20230274195A1 (en) Time-varying features via metadata
US12174840B2 (en) Optimizing the response time of data profiling in interactive sessions
US12189706B2 (en) Hybrid approach for generating recommendations
US12124483B2 (en) Data segmentation using clustering
US20230297861A1 (en) Graph recommendations for optimal model configurations
US20250348673A1 (en) Efficient multi-relation prediction with improved context computation
US12423329B2 (en) Cluster based node assignment in multi-dimensional feature space
US20230065616A1 (en) Techniques for schema drift detection
US20250077901A1 (en) Multi-output model based forecasting
US20260072909A1 (en) In-context learning for nl2sql with pattern based retrieval

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination