Explainable AI for the Choquet Integral

Murray, Bryce; Islam, Muhammad Aminul; Pinar, Anthony J.; Anderson, Derek T.; Scott, Grant; Havens, Timothy C.; Keller, James M.

doi:10.1109/tetci.2020.3005682

Cited by 27 publications

(12 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most AI and machine learning (ML) systems behave like black boxes as they fail to explain their decisions [11]. Incorporation of XAI in AI and ML systems requires attention to four system features: (i) the quality of inputs and interactions between them, (ii) method of combining the input information, (iii) the quality of the training data and, (iv) levels of trust users put in system decisions [11]. The AXAI capability framework proposed in part one of this paper and its implementation reported in the preceding sections of this part, exploited and relied on these four features.…”

Section: Discussionmentioning

confidence: 99%

“…It is proposed that four system features: the quality of inputs and interactions between them, the method of com-bining the input information, the quality of the training data and, trustworthiness of systems decisions would suffice incorporating the XAI in AI systems [11]. However, real-life use of these features for incorporating XAI in AI systems is not common yet.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Toward Accountable and Explainable Artificial Intelligence Part Two: The Framework Implementation

Khan¹,

Vice²

2022

Preprint

View full text Add to dashboard Cite

<div>This paper builds upon the theoretical foundations of the Accountable explainable Artificial Intelligence (AXAI) capability framework presented in part one of this paper. This part demonstrates the incorporation of the AXAI capability in the real time Affective State Assessment Module (ASAM) of a robotic system. The paper argues that adhering to the extreme Programming (XP) practices would help in understanding user behavior while systematically incorporating the AXAI capability in AI systems. Issues pertaining to identification of ethical, technical, functional, and domain-specific system requirements were resolved using an appropriate software design process, thus establishing confidence in the system. The presented ASAM synthesizes discrete and continuous models of affective state expressions and classifies them in real-time. Input, processed and output data are continuously shared with users via a graphical user interface (GUI) for providing reasons behind decisions. The GUI also disseminates information about local reasoning, data handling and decision-making. We hope this work will initiate further investigations on selection of suitable software design practices for incorporating the AXAI capability in AI systems, enhancing AI system acceptability and utility and, establishing a chain of responsibility.</div>

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Toward Accountable and Explainable Artificial Intelligence Part Two: The Framework Implementation

Khan¹,

Vice²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Nevertheless, the outputs provided by submodels are always treated equally in these two fusion strategies, which would enhance the contributions of worse outputs and do not explain the interaction between each classifier. Based on the benefits of the fuzzy integral [35], such as the explainable characteristics, it could explain not only the importance of each classifier but also the interaction between classifiers. For example, firstly, as shown in Figure 2, the red line could demonstrate the calculation order of fuzzy integral.…”

Section: Decision-level Fuzzy Fusion Strategymentioning

confidence: 99%

A Fuzzy Fusion Rotating Machinery Fault Diagnosis Framework Based on the Enhancement Deep Convolutional Neural Networks

Yang

Karimi

Gelman

2022

Sensors

View full text Add to dashboard Cite

Some artificial intelligence algorithms have gained much attention in the rotating machinery fault diagnosis due to their robust nonlinear regression properties. In addition, existing deep learning algorithms are usually dependent on single signal features, which would lead to the loss of some information or incomplete use of the information in the signal. To address this problem, three kinds of popular signal processing methods, including Fast Fourier Transform (FFT), Short-Time Fourier Transform (STFT) and directly slicing one-dimensional data into the two-dimensional matrix, are used to create four different datasets from raw vibration signal as the input data of four enhancement Convolutional Neural Networks (CNN) models. Then, a fuzzy fusion strategy is used to fuse the output of four CNN models that could analyze the importance of each classifier and explore the interaction index between each classifier, which is different from conventional fusion strategies. To show the performance of the proposed model, an artificial fault bearing dataset and a real-world bearing dataset are used to test the feature extraction capability of the model. The good anti-noise and interpretation characteristics of the proposed method are demonstrated as well.

show abstract

“…Meanwhile, several recent works propose methods of measuring and assessing explainability of machine learning and AI systems (Burkart & Huber, 2021). Nonetheless, recent literature cites AI systems as difficult to understand, adopt and trust (Murray et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Toward Accountable and Explainable Artificial Intelligence Part one: Theory and Examples

Khan¹,

Vice²

2022

Preprint

View full text Add to dashboard Cite

<div>After reviewing the current state of explainable Artificial Intelligence (XAI) capabilities in artificial Intelligence (AI) systems developed for critical domains like criminology, engineering, governance, health, law and psychology, this paper proposes a domain-independent Accountable explainable Artificial Intelligence (AXAI) capability framework. The proposed AXAI framework extends the XAI capability to let AI systems share their decisions and adequately explain the underlying reasoning processes. The idea is to help AI system developers overcome algorithmic biases and system limitations through incorporation of domain independent AXAI capabilities. Moreover, existing XAI methods would neither separate nor quantify measures of comprehensibility, accuracy and accountability so incorporating and assessing XAI capabilities remains difficult. Assessment of the AXAI capabilities of two AI systems in this paper demonstrates that the proposed AXAI framework facilitates separation and measurement of comprehensibility, predictive accuracy and accountability. The AXAI framework allows for the delineation of AI systems in a three-dimensional AXAI space. It measures comprehensibility as the readiness of a human to apply the acquired knowledge. The system accuracy is measured as the ratio of the test and training data, training data size and the observed number of false-positive inferences. Finally, the AXAI framework measures accountability in terms of the inspect ability of the input cues, the processed data and the output information, for addressing any legal and ethical issues.</div>

show abstract

Explainable AI for the Choquet Integral

Cited by 27 publications

References 41 publications

Toward Accountable and Explainable Artificial Intelligence Part Two: The Framework Implementation

Toward Accountable and Explainable Artificial Intelligence Part Two: The Framework Implementation

A Fuzzy Fusion Rotating Machinery Fault Diagnosis Framework Based on the Enhancement Deep Convolutional Neural Networks

Toward Accountable and Explainable Artificial Intelligence Part one: Theory and Examples

Contact Info

Product

Resources

About