Considering the potential of tools such as ChatGPT or Gemini to generate texts in a similar way to a human would do, having reliable detectors of AI -AI-generated content (AIGC)- is vital to combat the misuse and the ...
详细信息
In the realm of data sharing, effective data discovery is critical for fostering collaboration and innovation across organizations. Data spaces merge the interoperability and secure sharing features of data ecosystems...
详细信息
Even now, users with disabilities encounter serious barriers when accessing the Web. In particular, blind and visually impaired users encounter difficulties browsing and reading the contents of a website. Screen reade...
详细信息
As reliance on Machine Learning (ML) systems in real-world decision-making processes grows, ensuring these systems are free of bias against sensitive demographic groups is of increasing importance. Existing techniques...
As reliance on Machine Learning (ML) systems in real-world decision-making processes grows, ensuring these systems are free of bias against sensitive demographic groups is of increasing importance. Existing techniques for automatically debiasing ML models generally require access to either the models' internal architectures, the models' training datasets, or both. In this paper we outline the reasons why such requirements are disadvantageous, and present an alternative novel debiasing system that is both data- and model-agnostic. We implement this system as a Reinforcement Learning Agent and through extensive experiments show that we can debias a variety of target ML model architectures over three benchmark datasets. Our results show performance comparable to data- and/or model-gnostic state-of-the-art debiasers.
This paper presents the initial foundations of a new Global approach to Artificial Intelligence based on the modeling of global intelligence and the development of artificial cooperative systems to support this. The r...
详细信息
Considering the immense pace in machine learning (ML) technology and related products, it may be difficult to imagine a software system, including healthcare systems, without any subsystem containing an ML model in th...
详细信息
Purpose: This study introduces the Digital Maturity Assessment Model (DMAM), a model tailored to assess the digital maturity of SMEs, tracing its development from addressing business challenges to establishing a compa...
详细信息
The rapid growth of machine learning(ML)across fields has intensified the challenge of selecting the right algorithm for specific tasks,known as the Algorithm Selection Problem(ASP).Traditional trial-and-error methods...
详细信息
The rapid growth of machine learning(ML)across fields has intensified the challenge of selecting the right algorithm for specific tasks,known as the Algorithm Selection Problem(ASP).Traditional trial-and-error methods have become impractical due to their resource *** Machine Learning(AutoML)systems automate this process,but often neglect the group structures and sparsity in meta-features,leading to inefficiencies in algorithm recommendations for classification *** paper proposes a meta-learning approach using Multivariate Sparse Group Lasso(MSGL)to address these *** method models both within-group and across-group sparsity among meta-features to manage high-dimensional data and reduce multicollinearity across eight meta-feature *** Fast Iterative Shrinkage-Thresholding Algorithm(FISTA)with adaptive restart efficiently solves the non-smooth optimization *** validation on 145 classification datasets with 17 classification algorithms shows that our meta-learning method outperforms four state-of-the-art approaches,achieving 77.18%classification accuracy,86.07%recommendation accuracy and 88.83%normalized discounted cumulative gain.
Studies on evaluation metrics and LLM-as-a-Judge models for automatic text summarization have largely been focused on English, limiting our understanding of their effectiveness in other languages. Through our new data...
详细信息
暂无评论