The Role of Textualisation and Argumentation in Understanding the Machine Learning Process

Despite the broad adoption of Machine Learning models in many domains, they remain mostly black boxes. There is a pressing need to ensure Machine Learning models that are interpretable, so that designers and users can understand the reasons behind their predictions. In this work, we propose a new method called C-LORE-F to explain the decisions of fuzzy-based black box models. This new method uses some contextual information about the attributes as well as the knowledge of the fuzzy sets associated to the linguistic labels of the fuzzy attributes to provide actionable explanations. The experimental results on three datasets reveal the effectiveness of C-LORE-F when compared with the most relevant related works.

Download Full-text

Explaining Explainability: Interpretable machine learning for the behavioral sciences

10.31234/osf.io/9h6qr ◽

2021 ◽

Author(s):

Brendan Kennedy ◽

Nils Karl Reimer ◽

Morteza Dehghani

Keyword(s):

Machine Learning ◽

Predictive Accuracy ◽

Black Box ◽

Behavioral Sciences ◽

Interpretable Machine Learning ◽

Box Models ◽

Black Boxes ◽

Model Complex ◽

Complex Phenomena ◽

Black Box Models

Predictive data modeling is a critical practice for the behavioral sciences; however, it is under-practiced in part due to the incorrect view that machine learning (ML) models are "black boxes," unable to be used for inferential purposes. In this work, we present an argument for the adoption of techniques from interpretable Machine Learning (ML) by behavioral scientists. Our argument is structured around the dispelling of three misconceptions, or myths, about interpretability. First, while ML models' interpretability is often viewed dichotomously, being either interpretable (e.g., linear regression) or "black boxes" (e.g., neural networks), the reality is far more nuanced, affected by multiple factors which should jointly affect model choice. Second, we challenge the idea that interpretability is a necessary trade-off for predictive accuracy, reviewing recent methods from the field which are able to both model complex phenomena and expose the mechanism by which phenomena are related. And third, we present post hoc explanation, a recent approach that applies additional methods to black box models, countering the belief that black box models are inherently unusable for the behavioral sciences.

Download Full-text

Drug Classification using Black-box models and Interpretability

International Journal for Research in Applied Science and Engineering Technology ◽

10.22214/ijraset.2021.38203 ◽

2021 ◽

Vol 9 (9) ◽

pp. 1518-1529

Author(s):

Pooja Thakkar

Keyword(s):

Machine Learning ◽

Random Forest ◽

Decision Tree ◽

Learning Models ◽

Drug Classification ◽

Box Models ◽

Machine Learning Model ◽

Black Box Models ◽

Insight Into ◽

Machine Learning Models

Abstract: The focus of this study is on drug categorization utilising Machine Learning models, as well as interpretability utilizing LIME and SHAP to get a thorough understanding of the ML models. To do this, the researchers used machine learning models such as random forest, decision tree, and logistic regression to classify drugs. Then, using LIME and SHAP, they determined if these models were interpretable, which allowed them to better understand their results. It may be stated at the conclusion of this paper that LIME and SHAP can be utilised to get insight into a Machine Learning model and determine which attribute is accountable for the divergence in the outcomes. According to the LIME and SHAP results, it is also discovered that Random Forest and Decision Tree ML models are the best models to employ for drug classification, with Na to K and BP being the most significant characteristics for drug classification. Keywords: Machine Learning, Back-box models, LIME, SHAP, Decision Tree

Download Full-text

Explainable, Trustworthy, and Ethical Machine Learning for Healthcare: A Survey

10.36227/techrxiv.14376179.v1 ◽

2021 ◽

Author(s):

Khansa Rasheed ◽

Adnan Qayyum ◽

Mohammed Ghaly ◽

Ala Al-Fuqaha ◽

Adeel Razi ◽

...

Keyword(s):

Machine Learning ◽

Ethical Issues ◽

Black Box ◽

Healthcare Applications ◽

Ethical Problems ◽

Clinical Utilization ◽

Box Models ◽

Research Problems ◽

Further Development ◽

Black Box Models

With the advent of machine learning (ML) applications in daily life, the questions about liability, trust, and interpretability of their outputs are raising, especially for healthcare applications. The black-box nature of ML models is a roadblock for clinical utilization. Therefore, to gain the trust of clinicians and patients, researchers need to provide explanations of how and why the model is making a specific decision. With the promise of enhancing the trust and transparency of black-box models, researchers are in the phase of maturing the field of eXplainable ML (XML). In this paper, we provide a comprehensive review of explainable and interpretable ML techniques implemented for providing the reasons behind their decisions for various healthcare applications. Along with highlighting various security, safety, and robustness challenges that hinder the trustworthiness of ML we also discussed the ethical issues of healthcare ML and describe how explainable and trustworthy ML can resolve these ethical problems. Finally, we elaborate on the limitations of existing approaches and highlight various open research problems that require further development.

Download Full-text

Identifying the Machine Learning Family from Black-Box Models

Advances in Artificial Intelligence - Lecture Notes in Computer Science ◽

10.1007/978-3-030-00374-6_6 ◽

2018 ◽

pp. 55-65

Author(s):

Raül Fabra-Boluda ◽

Cèsar Ferri ◽

José Hernández-Orallo ◽

Fernando Martínez-Plumed ◽

María José Ramírez-Quintana

Keyword(s):

Machine Learning ◽

Black Box ◽

Box Models ◽

Black Box Models

Download Full-text

Hybrid Machine Learning Approaches and a Systematic Model Selection Process for Predicting Soot Emissions in Compression Ignition Engines

Energies ◽

10.3390/en14237865 ◽

2021 ◽

Vol 14 (23) ◽

pp. 7865

Author(s):

Saeid Shahpouri ◽

Armin Norouzi ◽

Christopher Hayduk ◽

Reza Rezaei ◽

Mahdi Shahbakhti ◽

...

Keyword(s):

Neural Network ◽

Machine Learning ◽

Feature Selection ◽

Black Box ◽

Box Model ◽

Feature Sets ◽

Machine Learning Methods ◽

Box Models ◽

Soot Emissions ◽

Black Box Models

The standards for emissions from diesel engines are becoming more stringent and accurate emission modeling is crucial in order to control the engine to meet these standards. Soot emissions are formed through a complex process and are challenging to model. A comprehensive analysis of diesel engine soot emissions modeling for control applications is presented in this paper. Physical, black-box, and gray-box models are developed for soot emissions prediction. Additionally, different feature sets based on the least absolute shrinkage and selection operator (LASSO) feature selection method and physical knowledge are examined to develop computationally efficient soot models with good precision. The physical model is a virtual engine modeled in GT-Power software that is parameterized using a portion of experimental data. Different machine learning methods, including Regression Tree (RT), Ensemble of Regression Trees (ERT), Support Vector Machines (SVM), Gaussian Process Regression (GPR), Artificial Neural Network (ANN), and Bayesian Neural Network (BNN) are used to develop the black-box models. The gray-box models include a combination of the physical and black-box models. A total of five feature sets and eight different machine learning methods are tested. An analysis of the accuracy, training time and test time of the models is performed using the K-means clustering algorithm. It provides a systematic way for categorizing the feature sets and methods based on their performance and selecting the best method for a specific application. According to the analysis, the black-box model consisting of GPR and feature selection by LASSO shows the best performance with test R2 of 0.96. The best gray-box model consists of SVM-based method with physical insight feature set along with LASSO for feature selection with test R2 of 0.97.

Download Full-text

The importance of ensuring artificial intelligence and machine learning can be understood at the human level

European Journal of Public Health ◽

10.1093/eurpub/ckz185.259 ◽

2019 ◽

Vol 29 (Supplement_4) ◽

Author(s):

S Ram

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Large Scale ◽

Clinical Decision Making ◽

Prediction Models ◽

Predictive Analytics ◽

Black Box ◽

User Engagement ◽

Box Models ◽

Black Box Models

Abstract With rapid developments in big data technology and the prevalence of large-scale datasets from diverse sources, the healthcare predictive analytics (HPA) field is witnessing a dramatic surge in interest. In healthcare, it is not only important to provide accurate predictions, but also critical to provide reliable explanations to the underlying black-box models making the predictions. Such explanations can play a crucial role in not only supporting clinical decision-making but also facilitating user engagement and patient safety. If users and decision makers do not have faith in the HPA model, it is highly likely that they will reject its use. Furthermore, it is extremely risky to blindly accept and apply the results derived from black-box models, which might lead to undesirable consequences or life-threatening outcomes in domains with high stakes such as healthcare. As machine learning and artificial intelligence systems are becoming more capable and ubiquitous, explainable artificial intelligence and machine learning interpretability are garnering significant attention among practitioners and researchers. The introduction of policies such as the General Data Protection Regulation (GDPR), has amplified the need for ensuring human interpretability of prediction models. In this talk I will discuss methods and applications for developing local as well as global explanations from machine learning and the value they can provide for healthcare prediction.

Download Full-text

A Short Survey on Machine Learning Explainability: An Application to Periocular Recognition

Electronics ◽

10.3390/electronics10151861 ◽

2021 ◽

Vol 10 (15) ◽

pp. 1861

Author(s):

João Brito ◽

Hugo Proença

Keyword(s):

Machine Learning ◽

Medical Image ◽

Visual Cues ◽

Medical Image Analysis ◽

Black Box ◽

Future Directions ◽

The Core ◽

Box Models ◽

Black Box Models ◽

Periocular Recognition

Interpretability has made significant strides in recent years, enabling the formerly black-box models to reach new levels of transparency. These kinds of models can be particularly useful to broaden the applicability of machine learning-based systems to domains where—apart from the predictions—appropriate justifications are also required (e.g., forensics and medical image analysis). In this context, techniques that focus on visual explanations are of particular interest here, due to their ability to directly portray the reasons that support a given prediction. Therefore, in this document, we focus on presenting the core principles of interpretability and describing the main methods that deliver visual cues (including one that we designed for periocular recognition in particular). Based on these intuitions, the experiments performed show explanations that attempt to highlight the most important periocular components towards a non-match decision. Then, some particularly challenging scenarios are presented to naturally sustain our conclusions and thoughts regarding future directions.

Download Full-text

Explainable, Trustworthy, and Ethical Machine Learning for Healthcare: A Survey

10.36227/techrxiv.14376179 ◽

2021 ◽

Author(s):

Khansa Rasheed ◽

Adnan Qayyum ◽

Mohammed Ghaly ◽

Ala Al-Fuqaha ◽

Adeel Razi ◽

...

Keyword(s):

Machine Learning ◽

Ethical Issues ◽

Black Box ◽

Healthcare Applications ◽

Ethical Problems ◽

Clinical Utilization ◽

Box Models ◽

Research Problems ◽

Further Development ◽

Black Box Models

With the advent of machine learning (ML) applications in daily life, the questions about liability, trust, and interpretability of their outputs are raising, especially for healthcare applications. The black-box nature of ML models is a roadblock for clinical utilization. Therefore, to gain the trust of clinicians and patients, researchers need to provide explanations of how and why the model is making a specific decision. With the promise of enhancing the trust and transparency of black-box models, researchers are in the phase of maturing the field of eXplainable ML (XML). In this paper, we provide a comprehensive review of explainable and interpretable ML techniques implemented for providing the reasons behind their decisions for various healthcare applications. Along with highlighting various security, safety, and robustness challenges that hinder the trustworthiness of ML we also discussed the ethical issues of healthcare ML and describe how explainable and trustworthy ML can resolve these ethical problems. Finally, we elaborate on the limitations of existing approaches and highlight various open research problems that require further development.

Download Full-text

O-098 Embryo selection using Artificial Intelligence (AI): Epistemic and ethical considerations

Human Reproduction ◽

10.1093/humrep/deab125.034 ◽

2021 ◽

Vol 36 (Supplement_1) ◽

Author(s):

M Afnan ◽

Y Liu ◽

V Conitzer ◽

C Rudin ◽

A Mishra ◽

...

Keyword(s):

Artificial Intelligence ◽

Machine Learning ◽

Ethical Issues ◽

Clinical Effectiveness ◽

Black Box ◽

Embryo Selection ◽

Societal Implications ◽

Ethical Considerations ◽

Box Models ◽

Black Box Models

Abstract Study question What are the epistemic and ethical considerations of clinically implementing Artificial Intelligence (AI) algorithms in embryo selection? Summary answer AI embryo selection algorithms used to date are “black-box” models with significant epistemic and ethical issues, and there are no trials assessing their clinical effectiveness. What is known already The innovation of time-lapse imaging offers the potential to generate vast quantities of data for embryo assessment. Computer Vision allows image data to be analysed using algorithms developed via machine learning which learn and adapt as they are exposed to more data. Most algorithms are developed using neural networks and are uninterpretable (or “black box”). Uninterpretable models are either too complicated to understand or proprietary, in which case comprehension is impossible for outsiders. In the IVF context, these outsiders include doctors, embryologists and patients, which raises ethical questions for its use in embryo selection. Study design, size, duration We performed a scoping review of articles evaluating AI for embryo selection in IVF. We considered the epistemic and ethical implications of current approaches. Participants/materials, setting, methods We searched Medline, Embase, ClinicalTrials.gov and the EU Clinical Trials Register for full text papers evaluating AI for embryo selection using the following key words: artificial intelligence* OR AI OR neural network* OR machine learning OR support vector machine OR automatic classification AND IVF OR in vitro fertilisation OR embryo*, as well as relevant MeSH and Emtree terms for Medline and Embase respectively. Main results and the role of chance We found no trials evaluating clinical effectiveness either published or registered. We found efficacy studies which looked at 2 types of outcomes – accuracy for predicting pregnancy or live birth and agreement with embryologist evaluation. Some algorithms were shown to broadly differentiate well between “good-” and “poor-” quality embryos but not between embryos of similar quality, which is the clinical need. Almost universally, the AI models were opaque (“black box”) in that at least some part of the process was uninterpretable. “Black box” models are problematic for epistemic and ethical reasons. Epistemic concerns include information asymmetries between algorithm developers and doctors, embryologists and patients; the risk of biased prediction caused by known and/or unknown confounders during the training process; difficulties in real-time error checking due to limited interpretability; the economics of buying into commercial proprietary models, brittle to variation in the treatment process; and an overall difficulty troubleshooting. Ethical pitfalls include the risk of misrepresenting patient values; concern for the health and well-being of future children; the risk of disvaluing disability; possible societal implications; and a responsibility gap, in the event of adverse events. Limitations, reasons for caution Our search was limited to the two main medical research databases. Although we checked article references for more publications, we were less likely to identify studies that were not indexed in Medline or Embase, especially if they were not cited in studies identified in our search. Wider implications of the findings It is premature to implement AI for embryo selection outside of a clinical trial. AI for embryo selection is potentially useful, but must be done carefully and transparently, as the epistemic and ethical issues are significant. We advocate for the use of interpretable AI models to overcome these issues. Trial registration number not applicable

Download Full-text