Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.7
2.9
Journals
Electronics
Special Issues
Explainable and Interpretable AI
share announcement

Explainable and Interpretable AI

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: 20 April 2024 | Viewed by 3760

Special Issue Editors

Dr. Atia Cortés

E-Mail Website
Guest Editor
Barcelona Supercomputing Center, 08034 Barcelona, Spain
Interests: Artificial Intelligence; AI ethics; machine learning; assistive technologies
Dr. Francisco Grimaldo

E-Mail Website
Guest Editor
Computer Science Department, Universitat de València, Av. de la Universitat s/n, 46100 Burjassot, Spain
Interests: computer science; Artificial Intelligence
Dr. Daniel Garcia-Costa

E-Mail Website
Guest Editor
Computer Science Department, Universitat de València, Av. de la Universitat s/n, 46100 Burjassot, Spain
Interests: computer science; artificial intelligence; natural language processing

Special Issue Information

Dear Colleagues,

Over the last few years, the European Union and its Member States have released several documents to define an ethical framework for Artificial Intelligence (AI) and a draft for a future regulation (the AI Act). Guidelines such as the Trustworthy AI Guidelines from the High-Level Expert Group and national strategies by EU Member States promote the inclusion of ethical principles such as fairness, accountability, or transparency. Accordingly, the AI community has been moving toward the operationalization of responsible practices of AI design, development, and use. In particular, the extended use of deep neural networks within applications that are now classified as high-risk by the AI Act, such as the use of facial recognition in law enforcement or healthcare, has raised several ethical and legal concerns regarding their design, but also the social and environmental impact. Indeed, these AI-based systems are also known as black-box or opaque models due to their lack of interpretability.

Explainable and interpretable AI (XAI/IAI) is an active area of research that aims to contribute to build a culture of best practices to achieve responsible and trustworthy AI. It focuses on developing methods to better understand the process behind the algorithms, while establishing levels of explainability adapted to different user-oriented audiences, enhancing the decision-making power of AI stakeholders by providing tools for assessment, understandability, and interaction with AI-based systems.

This Special Issue aims to collect high-quality, original state-of-the-art papers that present novel research including the following non-exhaustive list of topics:

  • Bias detection/evaluation/removal
  • Ethical and legal aspects of XAI/IAI
  • Evaluation metrics
  • Human-understandable explanations
  • Epistemic aspects of XAI
  • White-box approaches
  • Applications of XAI/IAI in different domains

Dr. Atia Cortés
Dr. Francisco Grimaldo
Dr. Daniel Garcia-Costa
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • bias detection/evaluation/removal
  • ethical and legal aspects of XAI/IAI
  • evaluation metrics
  • human-understandable explanations
  • epistemic aspects of XAI
  • white-box approaches
  • applications of XAI/IAI in different domains

Published Papers (4 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

19 pages, 1614 KiB  
Article
Explaining the Behaviour of Reinforcement Learning Agents in a Multi-Agent Cooperative Environment Using Policy Graphs
by Marc Domenech i Vila, Dmitry Gnatyshak, Adrian Tormos, Victor Gimenez-Abalos and Sergio Alvarez-Napagao
Electronics 2024, 13(3), 573; https://doi.org/10.3390/electronics13030573 - 31 Jan 2024
Viewed by 642
Abstract
The adoption of algorithms based on Artificial Intelligence (AI) has been rapidly increasing during the last few years. However, some aspects of AI techniques are under heavy scrutiny. For instance, in many use cases, it is not clear whether the decisions of an [...] Read more.
The adoption of algorithms based on Artificial Intelligence (AI) has been rapidly increasing during the last few years. However, some aspects of AI techniques are under heavy scrutiny. For instance, in many use cases, it is not clear whether the decisions of an algorithm are well informed and conforming to human understanding. Having ways to address these concerns is crucial in many domains, especially whenever humans and intelligent (physical or virtual) agents must cooperate in a shared environment. In this paper, we apply an explainability method based on the creation of a Policy Graph (PG) based on discrete predicates that represent and explain a trained agent’s behaviour in a multi-agent cooperative environment. We show that from these policy graphs, policies for surrogate interpretable agents can be automatically generated. These policies can be used to measure the reliability of the explanations enabled by the PGs through a fair behavioural comparison between the original opaque agent and the surrogate one. The contributions of this paper represent the first use case of policy graphs in the context of explaining agent behaviour in cooperative multi-agent scenarios and present experimental results that sets this kind of scenario apart from previous implementations in single-agent scenarios: when requiring cooperative behaviour, predicates that allow representing observations about the other agents are crucial to replicate the opaque agent’s behaviour and increase the reliability of explanations. Full article
(This article belongs to the Special Issue Explainable and Interpretable AI)
►▼ Show Figures

Figure 1

18 pages, 9604 KiB  
Article
INNT: Restricting Activation Distance to Enhance Consistency of Visual Interpretation in Neighborhood Noise Training
by Xingyu Wang, Rui Ma, Jinyuan He, Taisi Zhang, Xiajing Wang and Jingfeng Xue
Electronics 2023, 12(23), 4751; https://doi.org/10.3390/electronics12234751 - 23 Nov 2023
Viewed by 550
Abstract
In this paper, we propose an end-to-end interpretable neighborhood noise training framework (INNT) to address the issue of inconsistent interpretations between clean and noisy samples in noise training. Noise training conventionally involves incorporating noisy samples into the training set, followed by generalization training. [...] Read more.
In this paper, we propose an end-to-end interpretable neighborhood noise training framework (INNT) to address the issue of inconsistent interpretations between clean and noisy samples in noise training. Noise training conventionally involves incorporating noisy samples into the training set, followed by generalization training. However, visual interpretations suggest that models may be learning the noise distribution rather than the desired robust target features. To mitigate this problem, we reformulate the noise training objective to minimize the visual interpretation consistency of images in the sample neighborhood. We design a noise activation distance constraint regularization term to enforce the similarity of high-level feature maps between clean and noisy samples. Additionally, we enhance the structure of noise training by iteratively resampling noise to more accurately depict the sample neighborhood. Furthermore, neighborhood noise is introduced to achieve more intuitive sample neighborhood sampling. Finally, we conducted qualitative and quantitative tests on different CNN architectures and public datasets. The results indicate that INNT leads to a more consistent decision rationale and balances the accuracy between noisy and clean samples. Full article
(This article belongs to the Special Issue Explainable and Interpretable AI)
►▼ Show Figures

Figure 1

18 pages, 16934 KiB  
Article
Assessing Biases through Visual Contexts
by Anna Arias-Duart, Victor Gimenez-Abalos, Ulises Cortés and Dario Garcia-Gasulla
Electronics 2023, 12(14), 3066; https://doi.org/10.3390/electronics12143066 - 13 Jul 2023
Viewed by 837
Abstract
Bias detection in the computer vision field is a necessary task, to achieve fair models. These biases are usually due to undesirable correlations present in the data and learned by the model. Although explainability can be a way to gain insights into model [...] Read more.
Bias detection in the computer vision field is a necessary task, to achieve fair models. These biases are usually due to undesirable correlations present in the data and learned by the model. Although explainability can be a way to gain insights into model behavior, reviewing explanations is not straightforward. This work proposes a methodology to analyze the model biases without using explainability. By doing so, we reduce the potential noise arising from explainability methods, and we minimize human noise during the analysis of explanations. The proposed methodology combines images of the original distribution with images of potential context biases and analyzes the effect produced in the model’s output. For this work, we first presented and released three new datasets generated by diffusion models. Next, we used the proposed methodology to analyze the context impact on the model’s prediction. Finally, we verified the reliability of the proposed methodology and the consistency of its results. We hope this tool will help practitioners to detect and mitigate potential biases, allowing them to obtain more reliable models. Full article
(This article belongs to the Special Issue Explainable and Interpretable AI)
►▼ Show Figures

Figure 1

15 pages, 450 KiB  
Article
Multi-Class Fuzzy-LORE: A Method for Extracting Local and Counterfactual Explanations Using Fuzzy Decision Trees
by Najlaa Maaroof, Antonio Moreno, Aida Valls, Mohammed Jabreel and Pedro Romero-Aroca
Electronics 2023, 12(10), 2215; https://doi.org/10.3390/electronics12102215 - 12 May 2023
Viewed by 947
Abstract
Multi-class classification is a fundamental task in Machine Learning. However, complex models can be viewed as black boxes, making it difficult to gain insight into how the model makes its predictions and build trust in its decision-making process. This paper presents a novel [...] Read more.
Multi-class classification is a fundamental task in Machine Learning. However, complex models can be viewed as black boxes, making it difficult to gain insight into how the model makes its predictions and build trust in its decision-making process. This paper presents a novel method called Multi-Class Fuzzy-LORE (mcFuzzy-LORE) for explaining the decisions made by multi-class fuzzy-based classifiers such as Fuzzy Random Forests (FRF). mcFuzzy-LORE is an adaptation of the Fuzzy-LORE method that uses fuzzy decision trees as an alternative to classical decision trees, providing interpretable, human-readable rules that describe the reasoning behind the model’s decision for a specific input. The proposed method was evaluated on a private dataset that was used to train an FRF-based multi-class classifier that assesses the risk of developing diabetic retinopathy in diabetic patients. The results show that mcFuzzy-LORE outperforms prior classical LORE-based methods in the generation of counterfactual instances. Full article
(This article belongs to the Special Issue Explainable and Interpretable AI)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop