書(shū)目名稱(chēng)Artificial Intelligence. ECAI 2023 International Workshops影響因子(影響力)學(xué)科排名
書(shū)目名稱(chēng)Artificial Intelligence. ECAI 2023 International Workshops網(wǎng)絡(luò)公開(kāi)度
書(shū)目名稱(chēng)Artificial Intelligence. ECAI 2023 International Workshops網(wǎng)絡(luò)公開(kāi)度學(xué)科排名
書(shū)目名稱(chēng)Artificial Intelligence. ECAI 2023 International Workshops被引頻次
書(shū)目名稱(chēng)Artificial Intelligence. ECAI 2023 International Workshops被引頻次學(xué)科排名
書(shū)目名稱(chēng)Artificial Intelligence. ECAI 2023 International Workshops年度引用
書(shū)目名稱(chēng)Artificial Intelligence. ECAI 2023 International Workshops年度引用學(xué)科排名
書(shū)目名稱(chēng)Artificial Intelligence. ECAI 2023 International Workshops讀者反饋
書(shū)目名稱(chēng)Artificial Intelligence. ECAI 2023 International Workshops讀者反饋學(xué)科排名
作者: CANON 時(shí)間: 2025-3-21 23:10 作者: HERE 時(shí)間: 2025-3-22 03:06
Evaluation of?Human-Understandability of?Global Model Explanations Using Decision Treestic and local explanation approaches are deemed interpretable and sufficient in many applications. However, in domains like healthcare, where end users are patients without AI or domain expertise, there is an urgent need for model explanations that are more comprehensible and instil trust in the mo作者: Merited 時(shí)間: 2025-3-22 06:37 作者: Insatiable 時(shí)間: 2025-3-22 10:49 作者: justify 時(shí)間: 2025-3-22 13:50
Towards Explainable Deep Domain Adaptation Transfer learning and, in particular, domain adaptation allows to overcome this issue, by adapting the source model to a new target data distribution and therefore generalizing the knowledge from source to target domain. In this work, we present a method that makes the adaptation process more trans作者: 物質(zhì) 時(shí)間: 2025-3-22 18:52 作者: 權(quán)宜之計(jì) 時(shí)間: 2025-3-23 01:12
Deep Reinforcement Learning of?Autonomous Control Actions to?Improve Bus-Service Regularityat buses operating on the same route start to catch up with each other, severely impacting the regularity and the quality of the service. Control actions such as Bus Holding and Stop Skipping can be used to regulate the service and adjust the headway between two buses. Traditionally, this phenomenon作者: 多節(jié) 時(shí)間: 2025-3-23 03:15 作者: 防止 時(shí)間: 2025-3-23 09:22 作者: DOTE 時(shí)間: 2025-3-23 13:36 作者: Adjourn 時(shí)間: 2025-3-23 15:03 作者: 暫時(shí)過(guò)來(lái) 時(shí)間: 2025-3-23 18:24 作者: 不安 時(shí)間: 2025-3-24 00:15
Temporal Saliency Detection Towards Explainable Transformer-Based Timeseries Forecastingllenge, especially towards explainability. Focusing on commonly used saliency maps in explaining DNN in general, our quest is to build attention-based architecture that can automatically encode saliency-related temporal patterns by establishing connections with appropriate attention heads. Hence, th作者: 欄桿 時(shí)間: 2025-3-24 05:07
Explaining Taxi Demand Prediction Models Based on?Feature Importanceem, which is difficult due to its multivariate input and output space. As these models are composed of multiple layers, their predictions become opaque. This opaqueness makes debugging, optimising, and using the models difficult. To address this, we propose the usage of eXplainable AI (XAI) – featur作者: 消息靈通 時(shí)間: 2025-3-24 09:11
Bayesian CAIPI: A Probabilistic Approach to?Explanatory and?Interactive Machine Learningart algorithm, captures the user feedback and iteratively biases a data set toward a correct decision-making mechanism using counterexamples. The counterexample generation procedure relies on hand-crafted data augmentation and might produce implausible instances. We propose Bayesian CAIPI that embed作者: Gleason-score 時(shí)間: 2025-3-24 13:02 作者: 啪心兒跳動(dòng) 時(shí)間: 2025-3-24 14:49
A. M. Gaines,B. A. Peterson,O. F. Mendoza augment the predictive capabilities of hypercube-based SKE techniques, striving for a completeness rate of 100%. Furthermore, the study includes experiments that assess the effectiveness of the proposed enhancements.作者: Innovative 時(shí)間: 2025-3-24 20:40
https://doi.org/10.1007/978-3-319-76864-9 ability to generate such surrogate models. We investigate fidelity, interpretability, stability, and the algorithms’ capability to capture interaction effects through appropriate splits. Based on our comprehensive analyses, we finally provide an overview of user-specific recommendations.作者: coagulation 時(shí)間: 2025-3-25 02:48
https://doi.org/10.1007/978-3-319-76321-7where we distinguish ones from sevens, we show that Bayesian CAIPI matches the predictive accuracy of both, traditional CAIPI and default deep learning. Moreover, it outperforms both in terms of explanation quality.作者: Flatter 時(shí)間: 2025-3-25 06:50 作者: 讓空氣進(jìn)入 時(shí)間: 2025-3-25 11:31
Achieving Complete Coverage with?Hypercube-Based Symbolic Knowledge-Extraction Techniques augment the predictive capabilities of hypercube-based SKE techniques, striving for a completeness rate of 100%. Furthermore, the study includes experiments that assess the effectiveness of the proposed enhancements.作者: RLS898 時(shí)間: 2025-3-25 12:45
Leveraging Model-Based Trees as?Interpretable Surrogate Models for?Model Distillation ability to generate such surrogate models. We investigate fidelity, interpretability, stability, and the algorithms’ capability to capture interaction effects through appropriate splits. Based on our comprehensive analyses, we finally provide an overview of user-specific recommendations.作者: 類(lèi)人猿 時(shí)間: 2025-3-25 18:10 作者: Peristalsis 時(shí)間: 2025-3-25 20:28 作者: floodgate 時(shí)間: 2025-3-26 02:44 作者: 種族被根除 時(shí)間: 2025-3-26 05:49
https://doi.org/10.1007/978-1-4613-1173-7te the approach’s effectiveness on real-world driving data and demonstrate its ability to identify critical driving situations successfully. Moreover, we discuss the challenges associated with the approach and outline future research activities.作者: Foment 時(shí)間: 2025-3-26 08:32 作者: Baffle 時(shí)間: 2025-3-26 12:39 作者: staging 時(shí)間: 2025-3-26 18:16
Identifying Critical Scenarios in?Autonomous Driving During Operationte the approach’s effectiveness on real-world driving data and demonstrate its ability to identify critical driving situations successfully. Moreover, we discuss the challenges associated with the approach and outline future research activities.作者: GRUEL 時(shí)間: 2025-3-26 23:08 作者: 典型 時(shí)間: 2025-3-27 02:34 作者: Misgiving 時(shí)間: 2025-3-27 07:32
Abhandlungen zur Literaturwissenschaftproach that is best suited for a given context. This paper aims to address the challenge of selecting the most appropriate explainer given the context in which an explanation is required. For AI explainability to be effective, explanations and how they are presented needs to be oriented towards the 作者: 結(jié)果 時(shí)間: 2025-3-27 12:12
https://doi.org/10.1007/978-3-7091-9528-4lative importance of input features. While based on a solid mathematical foundation derived from cooperative game theory, SVs have a significant drawback: high computational cost. Calculating the exact SV is an NP-hard problem, necessitating the use of approximations, particularly when dealing with 作者: enchant 時(shí)間: 2025-3-27 15:57
?anna P. Pastuchova,Alexander G. Rach?tadtstic and local explanation approaches are deemed interpretable and sufficient in many applications. However, in domains like healthcare, where end users are patients without AI or domain expertise, there is an urgent need for model explanations that are more comprehensible and instil trust in the mo作者: Demulcent 時(shí)間: 2025-3-27 19:33
https://doi.org/10.1007/978-3-662-34000-4ainability techniques is low due to the lack of optimal evaluation measures. Without rigorous measures, it is hard to have concrete evidence of whether the new explanation techniques can significantly outperform their predecessors. Our study proposes a new taxonomy for evaluating local explanations:作者: 襲擊 時(shí)間: 2025-3-27 23:58
https://doi.org/10.1007/978-3-662-34000-4 and anomalies itself. Such data is often highly imbalanced and the availability of labels is limited. The data is generated in streaming fashion, which means that it is unbounded and potentially infinite. The industrial process may evolve over time due to degradation of the asset, maintenance actio作者: Anticoagulant 時(shí)間: 2025-3-28 03:17 作者: tendinitis 時(shí)間: 2025-3-28 07:41 作者: Hypopnea 時(shí)間: 2025-3-28 12:19
https://doi.org/10.1007/978-1-4615-5861-3at buses operating on the same route start to catch up with each other, severely impacting the regularity and the quality of the service. Control actions such as Bus Holding and Stop Skipping can be used to regulate the service and adjust the headway between two buses. Traditionally, this phenomenon作者: Facet-Joints 時(shí)間: 2025-3-28 16:47 作者: Mnemonics 時(shí)間: 2025-3-28 19:11
A. M. Gaines,B. A. Peterson,O. F. Mendoza models by generating human-understandable explanations. The existing literature encompasses a diverse range of techniques, each relying on specific theoretical assumptions and possessing its own advantages and disadvantages. Amongst the available choices, hypercube-based SKE techniques are notable 作者: 表否定 時(shí)間: 2025-3-29 01:11
Analog weight adaptation hardware,and potential of interpretable machine learning, in particular PIP-Net, for automated diagnosis support on real-world medical imaging data. PIP-Net learns human-understandable prototypical image parts and we evaluate its accuracy and interpretability for fracture detection and skin cancer diagnosis.作者: auxiliary 時(shí)間: 2025-3-29 06:08
The Vector Decomposition Method,hods, they frequently assign importance to features which lack causal influence on the outcome variable. Selecting causally relevant features among those identified as relevant by these methods, or even before model training, would offer a solution. Feature selection methods utilizing information th作者: 苦笑 時(shí)間: 2025-3-29 08:37
https://doi.org/10.1007/978-3-319-76864-9is paper focuses on using model-based trees as surrogate models which partition the feature space into interpretable regions via decision rules. Within each region, interpretable models based on additive main effects are used to approximate the behavior of the black box model, striking for an optima作者: 補(bǔ)助 時(shí)間: 2025-3-29 11:51 作者: 復(fù)習(xí) 時(shí)間: 2025-3-29 19:18 作者: Connotation 時(shí)間: 2025-3-29 23:10 作者: 葡萄糖 時(shí)間: 2025-3-30 01:47
Artificial Intelligence. ECAI 2023 International Workshops978-3-031-50396-2Series ISSN 1865-0929 Series E-ISSN 1865-0937 作者: 從容 時(shí)間: 2025-3-30 06:57
https://doi.org/10.1007/978-3-031-50396-2Artificial Intelligence; Machine Learning; Multi-Agent Systems; Reliability of Artificial Intelligence; 作者: EVICT 時(shí)間: 2025-3-30 08:33
978-3-031-50395-5The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerl作者: 責(zé)怪 時(shí)間: 2025-3-30 16:22
Communications in Computer and Information Sciencehttp://image.papertrans.cn/b/image/162559.jpg作者: CHART 時(shí)間: 2025-3-30 19:33 作者: Allergic 時(shí)間: 2025-3-30 21:46 作者: Retrieval 時(shí)間: 2025-3-31 01:20
Abhandlungen zur Literaturwissenschaftting of a given mental model of the relevant stakeholder, a reasoner component that solves the argumentation problem generated by a multi-explainer component, and an AI model that is to be explained suitably to the stakeholder of interest. By formalizing supporting premises—and inferences—we can map作者: Devastate 時(shí)間: 2025-3-31 08:47 作者: Folklore 時(shí)間: 2025-3-31 11:45 作者: bronchodilator 時(shí)間: 2025-3-31 17:23
https://doi.org/10.1007/978-3-662-34000-4on module. We consider two different approaches towards the utilization of machine learning model – online and offline. We present our work in relation to a cold rolling process use case, which is one of the steps in production of steel strips.作者: IST 時(shí)間: 2025-3-31 18:42 作者: canvass 時(shí)間: 2025-4-1 01:25 作者: fledged 時(shí)間: 2025-4-1 05:52
The Vector Decomposition Method,e variable. Specifically, we introduce causal versions of entropy and mutual information, termed causal entropy and causal information gain, which are designed to assess how much control a feature provides over the outcome variable. These newly defined quantities capture changes in the entropy of a 作者: 恩惠 時(shí)間: 2025-4-1 09:06
