CN111553389A - 一种用于理解深度学习模型决策机制的决策树生成方法 - Google Patents
一种用于理解深度学习模型决策机制的决策树生成方法 Download PDFInfo
- Publication number
- CN111553389A CN111553389A CN202010271181.7A CN202010271181A CN111553389A CN 111553389 A CN111553389 A CN 111553389A CN 202010271181 A CN202010271181 A CN 202010271181A CN 111553389 A CN111553389 A CN 111553389A
- Authority
- CN
- China
- Prior art keywords
- decision tree
- contribution
- tree
- deep learning
- learning 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (7)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010271181.7A CN111553389B (zh) | 2020-04-08 | 2020-04-08 | 一种用于理解深度学习模型目标分类决策机制的决策树生成方法 |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010271181.7A CN111553389B (zh) | 2020-04-08 | 2020-04-08 | 一种用于理解深度学习模型目标分类决策机制的决策树生成方法 |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111553389A true CN111553389A (zh) | 2020-08-18 |
CN111553389B CN111553389B (zh) | 2023-06-13 |
Family
ID=72002322
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010271181.7A Active CN111553389B (zh) | 2020-04-08 | 2020-04-08 | 一种用于理解深度学习模型目标分类决策机制的决策树生成方法 |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111553389B (zh) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112116028A (zh) * | 2020-09-29 | 2020-12-22 | 联想(北京)有限公司 | 模型决策解释实现方法、装置及计算机设备 |
CN112270352A (zh) * | 2020-10-26 | 2021-01-26 | 中山大学 | 一种基于并行剪枝优化的决策树生成方法及装置 |
CN112766415A (zh) * | 2021-02-09 | 2021-05-07 | 第四范式(北京)技术有限公司 | 用于解释人工智能模型的方法、装置及系统 |
CN113240119A (zh) * | 2021-04-08 | 2021-08-10 | 南京大学 | 一种用于游戏ai策略解释的跨模型蒸馏装置 |
CN116662412A (zh) * | 2023-07-24 | 2023-08-29 | 云南电网能源投资有限责任公司 | 一种电网配用电大数据的数据挖掘方法 |
CN116704208A (zh) * | 2023-08-04 | 2023-09-05 | 南京理工大学 | 基于特征关系的局部可解释方法 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030069652A1 (en) * | 2001-10-05 | 2003-04-10 | Lee Shih-Jong J. | Regulation of hierarchic decisions in intelligent systems |
CN108491766A (zh) * | 2018-03-05 | 2018-09-04 | 中山大学 | 一种端到端的基于深度决策森林的人群计数方法 |
CN109886464A (zh) * | 2019-01-20 | 2019-06-14 | 东北电力大学 | 基于优化奇异值分解生成特征集的低信息损失短期风速预测方法 |
US20190279111A1 (en) * | 2018-03-09 | 2019-09-12 | Zestfinance, Inc. | Systems and methods for providing machine learning model evaluation by using decomposition |
-
2020
- 2020-04-08 CN CN202010271181.7A patent/CN111553389B/zh active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030069652A1 (en) * | 2001-10-05 | 2003-04-10 | Lee Shih-Jong J. | Regulation of hierarchic decisions in intelligent systems |
CN108491766A (zh) * | 2018-03-05 | 2018-09-04 | 中山大学 | 一种端到端的基于深度决策森林的人群计数方法 |
US20190279111A1 (en) * | 2018-03-09 | 2019-09-12 | Zestfinance, Inc. | Systems and methods for providing machine learning model evaluation by using decomposition |
CN109886464A (zh) * | 2019-01-20 | 2019-06-14 | 东北电力大学 | 基于优化奇异值分解生成特征集的低信息损失短期风速预测方法 |
Non-Patent Citations (2)
Title |
---|
DAVID ALVAREZ-MELIS等: "On the Robustness of Interpretability Methods", 《ARXIV》, pages 66 - 71 * |
厉原通: "面向目标识别的深度学习模型理解方法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 04, pages 138 - 821 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112116028A (zh) * | 2020-09-29 | 2020-12-22 | 联想(北京)有限公司 | 模型决策解释实现方法、装置及计算机设备 |
CN112116028B (zh) * | 2020-09-29 | 2024-04-26 | 联想(北京)有限公司 | 模型决策解释实现方法、装置及计算机设备 |
CN112270352A (zh) * | 2020-10-26 | 2021-01-26 | 中山大学 | 一种基于并行剪枝优化的决策树生成方法及装置 |
CN112766415A (zh) * | 2021-02-09 | 2021-05-07 | 第四范式(北京)技术有限公司 | 用于解释人工智能模型的方法、装置及系统 |
CN113240119A (zh) * | 2021-04-08 | 2021-08-10 | 南京大学 | 一种用于游戏ai策略解释的跨模型蒸馏装置 |
CN113240119B (zh) * | 2021-04-08 | 2024-03-19 | 南京大学 | 一种用于游戏ai策略解释的跨模型蒸馏装置 |
CN116662412A (zh) * | 2023-07-24 | 2023-08-29 | 云南电网能源投资有限责任公司 | 一种电网配用电大数据的数据挖掘方法 |
CN116662412B (zh) * | 2023-07-24 | 2023-10-03 | 云南电网能源投资有限责任公司 | 一种电网配用电大数据的数据挖掘方法 |
CN116704208A (zh) * | 2023-08-04 | 2023-09-05 | 南京理工大学 | 基于特征关系的局部可解释方法 |
CN116704208B (zh) * | 2023-08-04 | 2023-10-20 | 南京理工大学 | 基于特征关系的局部可解释方法 |
Also Published As
Publication number | Publication date |
---|---|
CN111553389B (zh) | 2023-06-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111553389B (zh) | 一种用于理解深度学习模型目标分类决策机制的决策树生成方法 | |
Lines et al. | A shapelet transform for time series classification | |
CN108985380B (zh) | 一种基于聚类集成的转辙机故障识别方法 | |
CN109614495B (zh) | 一种结合知识图谱和文本信息的相关公司挖掘方法 | |
CN108132927A (zh) | 一种融合图结构与节点关联的关键词提取方法 | |
CN111931505A (zh) | 一种基于子图嵌入的跨语言实体对齐方法 | |
Tripoliti et al. | Modifications of the construction and voting mechanisms of the random forests algorithm | |
CN101196905A (zh) | 一种智能图形检索方法 | |
Sanz et al. | IIVFDT: Ignorance functions based interval-valued fuzzy decision tree with genetic tuning | |
CN109165672A (zh) | 一种基于渐进式学习的集成分类方法 | |
CN102682089A (zh) | 一种利用鉴别随机邻域嵌入分析的数据降维方法 | |
CN111062438A (zh) | 基于相关学习的图传播的弱监督细粒度图像分类算法 | |
CN116524960A (zh) | 一种基于混合熵下采样和集成分类器的语音情感识别系统 | |
Feng et al. | Fsrf: an improved random forest for classification | |
Nuiaa et al. | Evolving Dynamic Fuzzy Clustering (EDFC) to Enhance DRDoS_DNS Attacks Detection Mechnism. | |
Kim et al. | A daily tourism demand prediction framework based on multi-head attention CNN: The case of the foreign entrant in South Korea | |
CN113989544A (zh) | 一种基于深度图卷积网络的群体发现方法 | |
CN113743453A (zh) | 一种基于随机森林的人口数量预测方法 | |
CN113095501A (zh) | 一种基于深度强化学习的不平衡分类决策树生成方法 | |
CN115273645B (zh) | 一种室内面要素自动聚类的地图制图方法 | |
CN110502669A (zh) | 基于n边dfs子图的轻量级无监督图表示学习方法及装置 | |
CN112861692B (zh) | 一种房间分类模型构建方法及装置、房间分类方法及装置 | |
CN114970684A (zh) | 一种结合vae的提取网络核心结构的社区检测方法 | |
CN114708114A (zh) | 一种基于特征评价及改进算法的社交机器人账号检测方法 | |
Naitzat et al. | M-Boost: Profiling and refining deep neural networks with topological data analysis |
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 | ||
CB03 | Change of inventor or designer information | ||
CB03 | Change of inventor or designer information |
Inventor after: Wang Nianbin Inventor after: Liu Yang Inventor after: Zhang Yun Inventor after: Wang Hongbin Inventor after: Zhou Lianke Inventor after: Zhang Yi Inventor after: Li Yuantong Inventor before: Wang Nianbin Inventor before: Liu Yang Inventor before: Zhang Yun Inventor before: Wang Hongbin Inventor before: Zhou Lianke Inventor before: Zhang Yi Inventor before: Li Yuantong |
|
GR01 | Patent grant | ||
GR01 | Patent grant |