CN111553389B - 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 - Google Patents
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 Download PDFInfo
- Publication number
- CN111553389B CN111553389B CN202010271181.7A CN202010271181A CN111553389B CN 111553389 B CN111553389 B CN 111553389B CN 202010271181 A CN202010271181 A CN 202010271181A CN 111553389 B CN111553389 B CN 111553389B
- Authority
- CN
- China
- Prior art keywords
- decision tree
- tree
- contribution
- deep learning
- decision
- 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.)
- Active
Links
- 238000003066 decision tree Methods 0.000 title claims abstract description 92
- 238000000034 method Methods 0.000 title claims abstract description 71
- 238000013136 deep learning model Methods 0.000 title claims abstract description 56
- 230000007246 mechanism Effects 0.000 title claims abstract description 25
- 239000011159 matrix material Substances 0.000 claims abstract description 33
- 238000013138 pruning Methods 0.000 claims abstract description 20
- 238000000638 solvent extraction Methods 0.000 claims abstract description 5
- 230000008569 process Effects 0.000 claims description 19
- 235000008733 Citrus aurantifolia Nutrition 0.000 claims description 6
- 235000011941 Tilia x europaea Nutrition 0.000 claims description 6
- 239000004571 lime Substances 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 7
- 238000005192 partition Methods 0.000 abstract description 7
- 230000006870 function Effects 0.000 description 8
- 238000010276 construction Methods 0.000 description 7
- 244000141353 Prunus domestica Species 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 238000013145 classification model Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000003094 perturbing effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013140 knowledge distillation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Image Analysis (AREA)
Abstract
Description
Claims (5)
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 CN111553389A (zh) | 2020-08-18 |
CN111553389B true 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) |
Families Citing this family (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN116304702A (zh) * | 2021-02-09 | 2023-06-23 | 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 |
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 |
CN114004282B (zh) * | 2021-10-12 | 2024-12-03 | 武汉大学 | 一种电力系统深度强化学习紧急控制策略提取方法 |
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 |
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 |
CN118157795B (zh) * | 2024-03-06 | 2025-01-28 | 郑州铁路职业技术学院 | 基于不同类结构体作用多径产生机理的信道建模方法及系统 |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7031948B2 (en) * | 2001-10-05 | 2006-04-18 | Lee Shih-Jong J | Regulation of hierarchic decisions in intelligent systems |
WO2019173734A1 (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 (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
Non-Patent Citations (2)
Title |
---|
On the Robustness of Interpretability Methods;David Alvarez-Melis等;《arXiv》;66-71 * |
面向目标识别的深度学习模型理解方法研究;厉原通;《中国优秀硕士学位论文全文数据库信息科技辑》(第04期);I138-821 * |
Also Published As
Publication number | Publication date |
---|---|
CN111553389A (zh) | 2020-08-18 |
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 | |
Yang et al. | Global model interpretation via recursive partitioning | |
CN112365171B (zh) | 基于知识图谱的风险预测方法、装置、设备及存储介质 | |
CN109614495B (zh) | 一种结合知识图谱和文本信息的相关公司挖掘方法 | |
CN101093559A (zh) | 一种基于知识发现的专家系统构造方法 | |
Sanz et al. | IIVFDT: Ignorance functions based interval-valued fuzzy decision tree with genetic tuning | |
EP1903479B1 (en) | Method and system for data classification using a self-organizing map | |
Zheng et al. | Feature grouping and selection: A graph-based approach | |
CN101901251B (zh) | 基于马尔科夫过程亚稳性的复杂网络簇结构分析和识别方法 | |
CN113989544A (zh) | 一种基于深度图卷积网络的群体发现方法 | |
CN119088885A (zh) | 一种医疗领域知识图谱构建的方法 | |
CN109326328B (zh) | 一种基于谱系聚类的古生物谱系演化分析方法 | |
CN113742396A (zh) | 一种对象学习行为模式的挖掘方法及装置 | |
CN118522471A (zh) | 一种智能化肿瘤病程监控系统 | |
CN112487110A (zh) | 基于网络结构和节点内容的重叠社区演化分析方法及系统 | |
Nowak-Brzezińska | Enhancing the efficiency of a decision support system through the clustering of complex rule‐based knowledge bases and modification of the inference algorithm | |
CN113743453A (zh) | 一种基于随机森林的人口数量预测方法 | |
CN102004801A (zh) | 一种信息分类的方法 | |
CN117667890B (zh) | 一种用于标准数字化的知识库构建方法及系统 | |
Elwakil | Knowledge discovery based simulation system in construction | |
CN118093860A (zh) | 一种基于文本嵌入向量聚类的多层次科研主题挖掘方法 | |
CN117708711A (zh) | 基于多维度特征的在微博平台上识别社交机器人用户的方法及系统 | |
Ba-Alwi | Knowledge acquisition tool for learning membership function and fuzzy classification rules from numerical data | |
Liao et al. | An oil-immersed transformer fault diagnosis method based on data preprocessing and gradient boosting | |
CN114118299A (zh) | 一种结合相似性度量和社区发现的聚类方法 |
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 |
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 |
|
CB03 | Change of inventor or designer information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |