On the Challenges and Opportunities in Visualization for Machine Learning and Knowledge Extraction: A Research Agenda

Turkay, Çağatay; Laramee, Robert S.; Holzinger, Andreas

doi:10.1007/978-3-319-66808-6_13

Cited by 6 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Os modelos de aprendizagem podem ser descritos de diferentes formas, porém, para o objetivo de gerar conhecimento precisamos considerar os fatores cognitivos dos conhecedores do negócio [16] de modo que não se crie algo que fique obsoleto. Na minerac ¸ão de dados a visualizac ¸ão aumenta potencialmente a compreensibilidade e permite ac ¸ões posteriores ao que foi encontrado com os modelos de minerac ¸ão de dados [17].…”

Section: Visualizac ¸ãO Científica De Dadosunclassified

Uma Abordagem para Geração e Visualização de Regras de Associação de Acesso a Conteúdos de Portal de Notícias

Silva,

Guedes

2023

Anais Do XVI Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

This paper aims to develop and visually association rules through a data mining project approach, using a data set of history navigation contents of an online news portal of a Brazilian magazine. The rules found allow us to understand users and subscribers access trends sequences through frequent items by applying the Apriori algorithm. To achieve this objective, the concepts of exploratory data analysis – EDA, scientific data visualization, knowledge discovery in databses – KDD and association rules were used. The result is a dataset and and visualization using parallel bar diagrams for the association rules found which bring together the main features of publications to frequently read together in sequence.

show abstract

Section: Visualizac ¸ãO Científica De Dadosunclassified

Uma Abordagem para Geração e Visualização de Regras de Associação de Acesso a Conteúdos de Portal de Notícias

Silva,

Guedes

2023

Anais Do XVI Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

show abstract

“…Next, the scatter plot visualizations provide a higher level of transparency by offering the analyst contextual information about the current image's classification and degree of certainty within the population of images. Lastly, t-SNE, an approach commonly used in modern visualization tools [3,25,32,58] visualizes the population of images in an embedded feature space, again displaying the current image, its classification and degree of certainty within the larger population of dataset images.…”

Section: Visualizationsmentioning

confidence: 99%

In Automation We Trust: Investigating the Role of Uncertainty in Active Learning Systems

Iuzzolino,

Umada,

Ahmed

et al. 2020

Preprint

View full text Add to dashboard Cite

Fig. 1. We evaluate the role of classification uncertainty on analyst trust in active labeling systems. We visualize classification uncertainties using seven different techniques (a)-(e) designed to reveal increasing amounts of information about an algorithm's classification decisions and pair these visualizations with five different query policies. Our results suggest that active labeling system query policies and uncertainty visualizations can significantly influence analyst trust in the resulting classification.

show abstract

“…1) Data visualization for GCs: Data visualization (DV) is a graphic representation of data for modelers/users to understand the features of the data. In ML studies, DV is one of the most common techniques in modeling so that modelers are able to gain the related GCs for the design guidelines as well as for the interpretation to the response of models [158]. This technique can extend to the subjects of information visualization (IV) [159] or visual analytics (VA) [160].…”

Section: Extracting Graphic Gcsmentioning

confidence: 99%

Generalized Constraints as A New Mathematical Problem in Artificial Intelligence: A Review and Perspective

Hu,

2020

Preprint

View full text Add to dashboard Cite

In this comprehensive review, we describe a new mathematical problem in artificial intelligence (AI) from a mathematical modeling perspective, following the philosophy stated by Rudolf E. Kalman that "Once you get the physics right, the rest is mathematics". The new problem is called "Generalized Constraints (GCs)", and we adopt GCs as a general term to describe any type of prior information in modelings. To understand better about GCs to be a general problem, we compare them with the conventional constraints (CCs) and list their extra challenges over CCs. In the construction of AI machines, we basically encounter more often GCs for modeling, rather than CCs with well-defined forms. Furthermore, we discuss the ultimate goals of AI and redefine transparent, interpretable, and explainable AI in terms of comprehension levels about machines. We review the studies in relation to the GC problems although most of them do not take the notion of GCs. We demonstrate that if AI machines are simplified by a coupling with both knowledge-driven submodel and data-driven submodel, GCs will play a critical role in a knowledgedriven submodel as well as in the coupling form between the two submodels. Examples are given to show that the studies in view of a generalized constraint problem will help us perceive and explore novel subjects in AI, or even in mathematics, such as generalized constraint learning (GCL).

show abstract

On the Challenges and Opportunities in Visualization for Machine Learning and Knowledge Extraction: A Research Agenda

Cited by 6 publications

References 23 publications

Uma Abordagem para Geração e Visualização de Regras de Associação de Acesso a Conteúdos de Portal de Notícias

Uma Abordagem para Geração e Visualização de Regras de Associação de Acesso a Conteúdos de Portal de Notícias

In Automation We Trust: Investigating the Role of Uncertainty in Active Learning Systems

Generalized Constraints as A New Mathematical Problem in Artificial Intelligence: A Review and Perspective

Contact Info

Product

Resources

About