A survey of visual analytics for explainable artificial intelligence methods

G Alicioglu, B Sun - Computers & Graphics, 2022 - Elsevier
Deep learning (DL) models have achieved impressive performance in various domains such
as medicine, finance, and autonomous vehicle systems with advances in computing power …

State of the art of visual analytics for explainable deep learning

B La Rosa, G Blasilli, R Bourqui, D Auber… - Computer Graphics …, 2023 - Wiley Online Library
The use and creation of machine‐learning‐based solutions to solve problems or reduce
their computational costs are becoming increasingly widespread in many domains. Deep …

From" where" to" what": Towards human-understandable explanations through concept relevance propagation

R Achtibat, M Dreyer, I Eisenbraun, S Bosse… - arxiv preprint arxiv …, 2022 - arxiv.org
The emerging field of eXplainable Artificial Intelligence (XAI) aims to bring transparency to
today's powerful but opaque deep learning models. While local XAI methods explain …

Visual analytics for machine learning: A data perspective survey

J Wang, S Liu, W Zhang - IEEE Transactions on Visualization …, 2024 - ieeexplore.ieee.org
The past decade has witnessed a plethora of works that leverage the power of visualization
(VIS) to interpret machine learning (ML) models. The corresponding research topic, VIS4ML …

Automated detection of covid-19 using deep learning approaches with paper-based ecg reports

MM Bassiouni, I Hegazy, N Rizk… - Circuits, Systems, and …, 2022 - Springer
One of the pandemics that have caused many deaths is the Coronavirus disease 2019
(COVID-19). It first appeared in late 2019, and many deaths are increasing day by day until …

Topological deep learning: a review of an emerging paradigm

A Zia, A Khamis, J Nichols, UB Tayab, Z Hayder… - Artificial Intelligence …, 2024 - Springer
Topological deep learning (TDL) is an emerging area that combines the principles of
Topological data analysis (TDA) with deep learning techniques. TDA provides insight into …

Escape: Countering systematic errors from machine's blind spots via interactive visual analysis

Y Ahn, YR Lin, P Xu, Z Dai - Proceedings of the 2023 CHI Conference …, 2023 - dl.acm.org
Classification models learn to generalize the associations between data samples and their
target classes. However, researchers have increasingly observed that machine learning …

VA+ Embeddings STAR: A State‐of‐the‐Art Report on the Use of Embeddings in Visual Analytics

Z Huang, D Witschard, K Kucher… - Computer Graphics …, 2023 - Wiley Online Library
Over the past years, an increasing number of publications in information visualization,
especially within the field of visual analytics, have mentioned the term “embedding” when …

TopoBERT: Exploring the topology of fine-tuned word representations

A Rathore, Y Zhou, V Srikumar… - Information …, 2023 - journals.sagepub.com
Transformer-based language models such as BERT and its variants have found widespread
use in natural language processing (NLP). A common way of using these models is to fine …

VERB: Visualizing and interpreting bias mitigation techniques geometrically for word representations

A Rathore, S Dev, JM Phillips, V Srikumar… - ACM Transactions on …, 2024 - dl.acm.org
Word vector embeddings have been shown to contain and amplify biases in the data they
are extracted from. Consequently, many techniques have been proposed to identify …