Explanatory Interactive Machine Learning

Pfeuffer, Nicolas; Baum, Lorenz; Stammer, Wolfgang; Abdel-Karim, Benjamin M.; Schramowski, Patrick; Bucher, Andreas; Hügel, Christian; Rohde, Gernot; Kersting, Kristian; Hinz, Oliver

doi:10.1007/s12599-023-00806-x

Cited by 9 publications

(3 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, CNNs are applied for image-based cancer detection (e.g., Haenssle et al 2018). Within our literature population, two studies in which image data is processed with AI address health-related issues (Pfeuffer et al 2023;Zhang and Ram 2020). Another field that provides interesting use cases for computer vision is social media.…”

Section: Input Datamentioning

confidence: 99%

The role of artificial intelligence algorithms in information systems research: a conceptual overview and avenues for research

Bendig,

Bräunche

2024

Manag Rev Q

View full text Add to dashboard Cite

Artificial intelligence (AI) has made remarkable progress in the past decade. Despite the plethora of AI research, we lack an accrued overview of the extent to which management research uses AI algorithms. The context, purpose, and type of AI used in previous work remain unknown, though this information is critical to coordinating, extending, and strengthening the use of AI. We address this knowledge gap with a systematic literature review (SLR), focusing on 12 leading information systems (IS) journals and leveraging a customized generative pre-trained transformer (GPT) in our analyses. We propose a conceptual framework comprising eight dimensions to categorize our findings in terms of application areas, methods, and algorithms of applied AI, mitigating the lack of a concise AI taxonomy. Thus, we identify and discuss trends, outline underrepresented algorithms with significant potential, and derive research avenues. We extend the literature with a conceptual overview that may serve as a building block for theory building and further exploration of the evolving AI research domain.

show abstract

Section: Input Datamentioning

confidence: 99%

The role of artificial intelligence algorithms in information systems research: a conceptual overview and avenues for research

Bendig,

Bräunche

2024

Manag Rev Q

View full text Add to dashboard Cite

show abstract

“…In applications such as medical image classifications, deep learning models have been observed to focus on non-relevant or confounding parts of medical images such as artifacts for their classification or prediction outputs [11], [12]. In addition to promoting transparent learning process, XBL has the potential to unlearn such wrong correlations, which are termed as confounding regions, confounders, or spurious correlations (used interchangeably in this paper) [12], [13]; confounding regions are parts of training instances that are not correlated with a category, but incorrectly assumed to be so by a learner.…”

Section: A Explanation Based Learningmentioning

confidence: 99%

Impact of Feedback Type on Explanatory Interactive Learning

Hagos

Curran

Namee

2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Explanatory Interactive Learning (XIL) collects user feedback on visual model explanations to implement a Human-in-the-Loop (HITL) based interactive learning scenario. Different user feedback types will have different impacts on user experience and the cost associated with collecting feedback since different feedback types involve different levels of image annotation. Although XIL has been used to improve classification performance in multiple domains, the impact of different user feedback types on model performance and explanation accuracy is not well studied. To guide future XIL work we compare the effectiveness of two different user feedback types in image classification tasks: (1) instructing an algorithm to ignore certain spurious image features, and (2) instructing an algorithm to focus on certain valid image features. We use explanations from a Gradient-weighted Class Activation Mapping (GradCAM) based XIL model to support both feedback types. We show that identifying and annotating spurious image features that a model finds salient results in superior classification and explanation accuracy than user feedback that tells a model to focus on valid image features.

show abstract

“…It has received much attention over the past few years. The purpose of a model explanation is to clarify why the model makes a certain prediction, to increase confidence in the model’s predictions 10 and to describe exactly how a machine learning model achieves its properties. 11 Therefore, using machine learning explanations can increase the transparency, interpretability, fairness, robustness, privacy, trust and reliability of machine learning models.…”

Section: Introductionmentioning

confidence: 99%

Explainable machine learning for breast cancer diagnosis from mammography and ultrasound images: a systematic review

Gurmessa,

Jimma

2024

BMJ Health Care Inform

View full text Add to dashboard Cite

BackgroundBreast cancer is the most common disease in women. Recently, explainable artificial intelligence (XAI) approaches have been dedicated to investigate breast cancer. An overwhelming study has been done on XAI for breast cancer. Therefore, this study aims to review an XAI for breast cancer diagnosis from mammography and ultrasound (US) images. We investigated how XAI methods for breast cancer diagnosis have been evaluated, the existing ethical challenges, research gaps, the XAI used and the relation between the accuracy and explainability of algorithms.MethodsIn this work, Preferred Reporting Items for Systematic Reviews and Meta-Analyses checklist and diagram were used. Peer-reviewed articles and conference proceedings from PubMed, IEEE Explore, ScienceDirect, Scopus and Google Scholar databases were searched. There is no stated date limit to filter the papers. The papers were searched on 19 September 2023, using various combinations of the search terms ‘breast cancer’, ‘explainable’, ‘interpretable’, ‘machine learning’, ‘artificial intelligence’ and ‘XAI’. Rayyan online platform detected duplicates, inclusion and exclusion of papers.ResultsThis study identified 14 primary studies employing XAI for breast cancer diagnosis from mammography and US images. Out of the selected 14 studies, only 1 research evaluated humans’ confidence in using the XAI system—additionally, 92.86% of identified papers identified dataset and dataset-related issues as research gaps and future direction. The result showed that further research and evaluation are needed to determine the most effective XAI method for breast cancer.ConclusionXAI is not conceded to increase users’ and doctors’ trust in the system. For the real-world application, effective and systematic evaluation of its trustworthiness in this scenario is lacking.PROSPERO registration numberCRD42023458665.

show abstract

Explanatory Interactive Machine Learning

Cited by 9 publications

References 80 publications

The role of artificial intelligence algorithms in information systems research: a conceptual overview and avenues for research

The role of artificial intelligence algorithms in information systems research: a conceptual overview and avenues for research

Impact of Feedback Type on Explanatory Interactive Learning

Explainable machine learning for breast cancer diagnosis from mammography and ultrasound images: a systematic review

Contact Info

Product

Resources

About