Explainable AI and Interpretable Machine Learning: A Case Study in Perspective

Vishwarupe, Varad; Joshi, P.N.; Mathias, Nicole; Maheshwari, Shrey; Mhaisalkar, Shweta; Pawar, Vishal

doi:10.1016/j.procs.2022.08.105

Cited by 27 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SHAP framework plays a pivotal role in enhancing the interpretability of machine learning models, thereby facilitating responsible and ethical use of AI systems [42]. Details related to the mathematical framework underlying the calculation of SHAP values are presented in Ref.…”

Section: Model-agnostic Explainability Using Shap Frameworkmentioning

confidence: 99%

AutoML Insights: Gaining Confidence to Operationalize Predictive Models

Stoica,

Florentina Stoica

2024

The New Era of Business Intelligence [Working Title]

View full text Add to dashboard Cite

Automated machine learning (AutoML) tools empower organizations to unlock valuable new business insights, integrate advanced AI capabilities into applications, and enable both data scientists and non-technical experts to swiftly build predictive models. Complex models generated by AutoML can appear to operate as “black boxes.” This lack of transparency can be a major disadvantage in relation to compliance with the legislation (e.g., European Union regulations implementing a “right to explanation” of algorithmic decisions provided by artificial intelligence systems). Furthermore, in many applications one must not trust a black-box system by default. We approach the problem of confidence in models generated using AutoML frameworks in two areas: model explanation and model validation, respectively. To gain confidence in the results provided by the machine learning models provided by the AutoML pipelines, we propose a model-agnostic approach based on SHapley Additive exPlanations (SHAP) values for the interpretability of these models, from a global and local perspective. We conducted a comparative analysis of three AutoML frameworks, examining their architectures and practical aspects, which aims at transparency in the generation of automatic learning models. Transparent model generation helps stakeholders understand how models are created, leading to greater confidence in their reliability and suitability for deployment in real-world scenarios.

show abstract

Section: Model-agnostic Explainability Using Shap Frameworkmentioning

confidence: 99%

AutoML Insights: Gaining Confidence to Operationalize Predictive Models

Stoica,

Florentina Stoica

2024

The New Era of Business Intelligence [Working Title]

View full text Add to dashboard Cite

show abstract

“…To examine the model without affecting its efficiency, the method employs post hoc and intrinsic methods after training. A widely used explainable artificial intelligence method called local interpretable model-agnostic explanations (LIME) is adopted to explain the functioning of ML and deep learning (DL) models by providing localized, model-agnostic interpretations [18,19].…”

Section: Introductionmentioning

confidence: 99%

Recognition of Sunflower Diseases Using Hybrid Deep Learning and Its Explainability with AI

et al. 2023

View full text Add to dashboard Cite

Sunflower is a crop that has many economic values and ornamental usages. However, its production can be hampered due to various diseases such as downy mildew, gray mold, and leaf scars, and it is challenging for farmers to identify disease-prone conditions with traditional approaches. Thus, a computerized model composed of vision, artificial intelligence, and machine learning is the demand of the age to detect diseases in plants efficiently. In this paper, we develop a hybrid model with transfer learning (TL) and a simple CNN using a small dataset for detecting sunflower diseases. Out of the eight models tested on the dataset of four different classes (downy mildew, gray mold, leaf scars, and fresh leaf), the VGG19 + CNN hybrid model achieves the best results in terms of precision, recall, F1-score, accuracy, Hamming loss, Matthews coefficient, Jaccard score, and Cohen’s kappa metrics. The experimental outcomes show that the proposed model provides better precision, recall, and accuracy than other approaches on the benchmark dataset.

show abstract

“…XAI emphasizes that AI should have explainability, meaning that the model and its results can be explained in a way that humans can understand. XAI allows the interpretation of the learned model and analyzes its logical flow by focusing on the reasons that the system has a given demerit [ 7 ]. Simultaneously, a growing number of experts at the intersection of AI and healthcare have concluded that the ability of AI models to provide explanations to humans is more important than their accuracy when it comes to practical applications in clinical settings.…”

Section: Introductionmentioning

confidence: 99%

Grad-CAM-Based Explainable Artificial Intelligence Related to Medical Text Processing

Zhang,

Ogasawara

2023

Bioengineering

View full text Add to dashboard Cite

The opacity of deep learning makes its application challenging in the medical field. Therefore, there is a need to enable explainable artificial intelligence (XAI) in the medical field to ensure that models and their results can be explained in a manner that humans can understand. This study uses a high-accuracy computer vision algorithm model to transfer learning to medical text tasks and uses the explanatory visualization method known as gradient-weighted class activation mapping (Grad-CAM) to generate heat maps to ensure that the basis for decision-making can be provided intuitively or via the model. The system comprises four modules: pre-processing, word embedding, classifier, and visualization. We used Word2Vec and BERT to compare word embeddings and use ResNet and 1Dimension convolutional neural networks (CNN) to compare classifiers. Finally, the Bi-LSTM was used to perform text classification for direct comparison. With 25 epochs, the model that used pre-trained ResNet on the formalized text presented the best performance (recall of 90.9%, precision of 91.1%, and an F1 score of 90.2% weighted). This study uses ResNet to process medical texts through Grad-CAM-based explainable artificial intelligence and obtains a high-accuracy classification effect; at the same time, through Grad-CAM visualization, it intuitively shows the words to which the model pays attention when making predictions.

show abstract

Explainable AI and Interpretable Machine Learning: A Case Study in Perspective

Cited by 27 publications

References 7 publications

AutoML Insights: Gaining Confidence to Operationalize Predictive Models

AutoML Insights: Gaining Confidence to Operationalize Predictive Models

Recognition of Sunflower Diseases Using Hybrid Deep Learning and Its Explainability with AI

Grad-CAM-Based Explainable Artificial Intelligence Related to Medical Text Processing

Contact Info

Product

Resources

About