检索结果-内蒙古大学图书馆

Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bender, Sidney Anders, Christopher J. Chormai, Pattarawat Marxfeld, Heike Herrmann, Jan Montavon, Grégoire Machine Learning Group Technische Universität Berlin Germany BIFOLD – Berlin Institute for the Foundations of Learning and Data Berlin Germany Max Planck School of Cognition Leipzig Germany BASF SE Ludwigshafen am Rhein Germany Department of Mathematics and Computer Science Freie Universität Berlin Germany

This paper introduces a novel technique called counterfactual knowledge distillation (CFKD) to detect and remove reliance on confounders in deep learning models with the help of human expert feedback. Confounders are spurious features that models tend to rely on, which can result in unexpected errors in regulated or safety-critical domains. The paper highlights the benefit of CFKD in such domains and shows some advantages of counterfactual explanations over other types of explanations. We propose an experiment scheme to quantitatively evaluate the success of CFKD and different teachers that can give feedback to the model. We also introduce a new metric that is better correlated with true test performance than validation accuracy. The paper demonstrates the effectiveness of CFKD on synthetically augmented datasets and on real-world histopathological datasets. © 2023, CC0.

关键词： Distillation

Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation

学校读者我要写书评

暂无评论

Towards Fixing Clever-Hans Predictors with Counterfactual Kn...

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Sidney Bender Christopher J. Anders Pattarawat Chormai Heike Marxfeld Jan Herrmann Grégoire Montavon Machine Learning Group Technische Universität Berlin Germany BIFOLD – Berlin Institute for the Foundations of Learning and Data Berlin Germany Max Planck School of Cognition Leipzig Germany BASF SE Ludwigshafen am Rhein Germany Department of Mathematics and Computer Science Freie Universität Berlin Germany

关键词：

Optimal kernel choice for score function-based causal discovery 24

学校读者我要写书评

暂无评论

Optimal kernel choice for score function-based causal discov...

Proceedings of the 41st International Conference on machine learning

作者： Wenjie Wang Biwei Huang Feng Liu Xinge You Tongliang Liu Kun Zhang Mingming Gong School of Mathematics and Statistics The University of Melbourne Australia and Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Halicioğlu Data Science Institute (HDSI) University of California San Diego School of Computing and Information Systems The University of Melbourne Australia Huazhong University of Science and Technology China School of Computer Science Faculty of Engineering The University of Sydney Australia Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates and Department of Philosophy Carnegie Mellon University

Score-based methods have demonstrated their effectiveness in discovering causal relationships by scoring different causal structures based on their goodness of fit to the data. Recently, Huang et al. (2018) proposed a generalized score function that can handle general data distributions and causal relationships by modeling the relations in reproducing kernel Hilbert space (RKHS). The selection of an appropriate kernel within this score function is crucial for accurately characterizing causal relationships and ensuring precise causal discovery. However, the current method involves manual heuristic selection of kernel parameters, making the process tedious and less likely to ensure optimality. In this paper, we propose a kernel selection method within the generalized score function that automatically selects the optimal kernel that best fits the data. Specifically, we model the generative process of the variables involved in each step of the causal graph search procedure as a mixture of independent noise variables. Based on this model, we derive an automatic kernel selection method by maximizing the marginal likelihood of the variables involved in each search step. We conduct experiments on both synthetic data and real-world benchmarks, and the results demonstrate that our proposed method outperforms heuristic kernel selection methods.

关键词：

Role of machine learning in Climate Change Prediction and Mitigation

学校读者我要写书评

暂无评论

Role of Machine Learning in Climate Change Prediction and Mi...

machine learning and Autonomous Systems (ICMLAS), International Conference on

作者： Nayan Jikar Yash Tale Abhay Tale Aditya Barhate Prateek Verma Aman Jikar Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India Department of Computer Science and Engineering Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research Wardha Maharashtra India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Climate change is one of the biggest challenges of the 21st century, with profound environmental, economic, and social impacts. machine learning (ML) has emerged as a transformative tool to address climate challenges through data-driven solutions, offering predictive capabilities for extreme weather events and enhancing the efficiency of clean-energy systems. This technology benefits the optimization of renewable energy generation, intelligent grid management, and resource utilization towards reducing greenhouse gas emissions. Moreover, ML promotes climate justice through targeted region-specific intervention and inclusive solution-making for the most vulnerable. Several technical and ethical challenges associated with data quality, scalability, and model generalization must still be overcome for ML to realize its potential. This paper reviews the role of ML in climate change prediction and mitigation discusses ongoing real-world applications and outlines the future research agenda necessary to address existing challenges. Integrating ML with emerging technologies like the Internet of Things (IoT) and explainable AI, alongside global collaboration and a focus on climate justice, will be essential in advancing effective climate action.

关键词： Climate change Renewable energy sources Ethics Prevention and mitigation Scalability data integrity Collaboration data models Internet of Things Meteorology

Cost-Effective Communication in UDN in Indoor and Outdoor Environment via machine learning

学校读者我要写书评

暂无评论

Cost-Effective Communication in UDN in Indoor and Outdoor En...

2023 International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering, ICECONF 2023

作者： Karman, K. Nattar Velmurugan, V. Raju, Kommisetti Murthy Sajana, T. Vijayalakshmi, V. Dhanraj, JoshuvaArockia Department of Artificial Intelligence and Machine Learning Saveetha School of Engineering Tamil Nadu Chennai602105 India Department of Electronics and Communication Engineering Vel Tech Rangarajan and Dr.Sagunthala RandD Institute of Science and Technology Tamil Nadu Chennai600062 India Department of Electronics and Communication Engineering Shri Vishnu Engineering College for Women Andhra Pradesh West Godavari India Department of Artificial Intelligence and Data Science KoneruLakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522502 India Department of Networking and Communications School of Computing SRM Institute of Science and Technology Tamil Nadu Kattankulathur603203 India Department of Mechatronics Engineering Hindustan Institute of Technology and Science Tamil Nadu Chennai603103 India

ISBN: (纸本)9798350334357

In general, applications on a densely populated network are slower. When there are no opportunities to interact with the devices on the network, the user is forced to communicate at some cost. Thus, the inconsistency that exists there increases the cost over that dense network. The single way to evaluate prospect usage is to look at that have used in the earlier period. This paper proposes an upgraded approach to upgrading existing services within the Ultra Dense cloud Network (UDN). In this way the cost for the services available there is calculated in advance and a system is developed to manage it effectively. This proposed method clearly shows that the effective cost can be managed by combining high-costservices and low-costservices separately. This will help to manage the various communication processes to achieve high effectiveness in Ultra Dense cloud Network (UDN). The proposed method achieves 93.28% of Cost-effective data Management.49% of Application log failure, 42 % of system log failure, 98% of network log management, 96% of security log management, 99% cost effective management. © 2023 IEEE.

关键词： Cost effectiveness

Predicting House Price Model : A Comprehensive Analysis with Random Forest and Decision Tree Method

学校读者我要写书评

暂无评论

Predicting House Price Model : A Comprehensive Analysis with...

Innovation in Technology (INOCON), IEEE International Conference for

作者： Mansi Sharma Deepak Sharma Rushikesh Burle Pawan Patil Isha Joge Chetan Puri Department of Computer Science and Design Datta Meghe Institute of Higher Education and Research Wardha India Department of Commerce & Management Sciences Datta Meghe Institute of Higher Education and Research(DU) Wardha Maharashtra Department of Artificial Intelligence and Machine Learning Datta Meghe Institute of Higher Education and Research Wardha India Department of Artificial Intelligence and Data Science Datta Meghe Institute of Higher Education and Research Wardha India

This paper explores the field of predicting property prices through a thorough comparison of several regression techniques. Linear regression, decision tree regression, random forest regression, K-neighbors regression, gradient boosting regression, and XGBoost regression are the regression models that are being examined. Finding the best model to reliably estimate house prices based on a set of features is the *** dataset used in this study includes location, bedroom count, square footage, and other relevant parameters that are known to affect property values. Each regression model is trained and tested on this dataset using a methodical evaluation procedure, and its performance is evaluated using important metrics including R-squared, Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and overall correctness. predicting house prices mainly use harlfoxem (Owner) repository of housing dataset will contain the homes sold between May 2014 and May 2015 with 21613 entries and 21 attribute were used to evaluate the performance of machine learning prediction model. For practitioners and scholars working in real estate, housing market analysis, and related sectors, this study offers insightful information. It emphasizes how crucial it is to properly choose regression techniques depending on the particulars of the prediction task and the distinct qualities of the dataset.

关键词：

Existence of Direct Density Ratio Estimators

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Banzato, Erika Drton, Mathias Saraf-Poor, Kian Shi, Hongjian Department of Statistical Sciences University of Padova Italy TUM School of Computation Information and Technology Munich Data Science Institute Technical University of Munich Munich Center for Machine Learning Germany Department of Statistics Columbia University United States TUM School of Computation Information and Technology Technical University of Munich Germany

Many two-sample problems call for a comparison of two distributions from an exponential family. Density ratio estimation methods provide ways to solve such problems through direct estimation of the differences in natural parameters. The term direct indicates that one avoids estimating both marginal distributions. In this context, we consider the Kullback–Leibler Importance Estimation Procedure (KLIEP), which has been the subject of recent work on differential networks. Our main result shows that the existence of the KLIEP estimator is characterized by whether the average sufficient statistic for one sample belongs to the convex hull of the set of all sufficient statistics for data points in the second sample. For high-dimensional problems it is customary to regularize the KLIEP loss by adding the product of a tuning parameter and a norm of the vector of parameter differences. We show that the existence of the regularized KLIEP estimator requires the tuning parameter to be no less than the dual norm-based distance between the average sufficient statistic and the convex hull. The implications of these existence issues are explored in applications to differential network analysis. Copyright © 2025, The Authors. All rights reserved.

关键词： Parameter estimation

UNCERTAINTY QUANTIFICATION FOR LEARNED ISTA

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hoppe, Frederik Verdun, Claudio Mayrink Laus, Hannah Krahmer, Felix Rauhut, Holger Mathematics of Information Processing RWTH Aachen University Aachen Germany Department of Mathematics Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Munich Data Science Institute Technical University of Munich Munich Germany

Model-based deep learning solutions to inverse problems have attracted increasing attention in recent years as they bridge state-of-the-art numerical performance with interpretability. In addition, the incorporated prior domain knowledge can make the training more efficient as the smaller number of parameters allows the training step to be executed with smaller datasets. Algorithm unrolling schemes stand out among these model-based learning techniques. Despite their rapid advancement and their close connection to traditional high-dimensional statistical methods, they lack certainty estimates and a theory for uncertainty quantification is still elusive. This work provides a step towards closing this gap proposing a rigorous way to obtain confidence intervals for the LISTA estimator. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

Explainable Artificial Intelligence for Medical Applications: A Review

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Sun, Qiyang Akman, Alican Schuller, Björn W. Technical University of Munich Munich Data Science Institute Munich Center for Machine Learning Munich Germany Imperial College London London United Kingdom Huxley Building 180 Queen's Gate South Kensington LondonSW7 2AZ United Kingdom

The continuous development of artificial intelligence (AI) theory has propelled this field to unprecedented heights, owing to the relentless efforts of scholars and researchers. In the medical realm, AI takes a pivotal role, leveraging robust machine learning (ML) algorithms. AI technology in medical imaging aids physicians in X-ray, computed tomography (CT) scans, and magnetic resonance imaging (MRI) diagnoses, conducts pattern recognition and disease prediction based on acoustic data, delivers prognoses on disease types and developmental trends for patients, and employs intelligent health management wearable devices with human-computer interaction technology to name but a few. While these well-established applications have significantly assisted in medical field diagnoses, clinical decision-making, and management, collaboration between the medical and AI sectors faces an urgent challenge: How to substantiate the reliability of decision-making? The underlying issue stems from the conflict between the demand for accountability and result transparency in medical scenarios and the black-box model traits of AI. This article reviews recent research grounded in explainable artificial intelligence (XAI), with an emphasis on medical practices within the visual, audio, and multimodal perspectives. We endeavour to categorise and synthesise these practices, aiming to provide support and guidance for future researchers and healthcare professionals. © 2024, CC BY-NC-SA.

关键词： Wearable computers