The black-box nature of deep neural networks (DNNs) makes it impossible to understand why a particular output is produced, creating demand for "Explainable AI". In this paper, we show that statistical fault localization (SFL) techniques from software engineering deliver high quality explanations of the outputs of DNNs, where we define an explanation as a minimal subset of features sufficient for making the same decision as for the original input. We present an algorithm and a tool called DeepCover, which synthesizes a ranking of the features of the inputs using SFL and constructs explanations for the decisions of the DNN based on this ranking. We compare explanations produced by DeepCover with those of the state-of-the-art tools GradCAM, LIME, SHAP, RISE and Extremal and show that explanations generated by DeepCover are consistently better across a broad set of experiments. On a benchmark set with known ground truth, DeepCover achieves 76.7% accuracy, which is 6% better than the second best Extremal.
While machine learning models are usually assumed to always output a prediction, there also exist extensions in the form of reject options which allow the model to reject inputs where only a prediction with an unacceptably low certainty would be possible. With the ongoing rise of eXplainable AI, a lot of methods for explaining model predictions have been developed. However, understanding why a given input was rejected, instead of being classified by the model, is also of interest. Surprisingly, explanations of rejects have not been considered so far. We propose to use counterfactual explanatio…
University of Toulouse（图卢兹大学）；IRIT, CNRS（法国国家科学研究中心图卢兹计算机科学研究所）
Despite the progress observed with model-agnostic explainable AI (XAI), it is the case that model-agnostic XAI can produce incorrect explanations. One alternative are the so-called formal approaches to XAI, that include PI-explanations. Unfortunately, PI-explanations also exhibit important drawbacks, the most visible of which is arguably their size. The computation of relevant features serves to trade off probabilistic precision for the number of features in an explanation. However, even for very simple classifiers, the complexity of computing sets of relevant features is prohibitive. This pap…
With the advent of Industry 4.0, Data Science and Explainable Artificial Intelligence (XAI) has received considerable intrest in recent literature. However, the entry threshold into XAI, in terms of computer coding and the requisite mathematical apparatus, is really high. For fault diagnosis of steel plates, this work reports on a methodology of incorporating XAI based insights into the Data Science process of development of high precision classifier. Using Synthetic Minority Oversampling Technique (SMOTE) and notion of medoids, insights from XAI tools viz. Ceteris Peribus profiles, Partial De…
University College Dublin（都柏林大学学院）；Insight Centre for Data Analytics, UCD（UCD洞察数据分析中心）；ML Labs, SFI CRT（SFI CRT机器学习实验室）
Very few eXplainable AI (XAI) studies consider how users understanding of explanations might change depending on whether they know more or less about the to be explained domain (i.e., whether they differ in their expertise). Yet, expertise is a critical facet of most high stakes, human decision making (e.g., understanding how a trainee doctor differs from an experienced consultant). Accordingly, this paper reports a novel, user study (N=96) on how peoples expertise in a domain affects their understanding of post-hoc explanations by example for a deep-learning, black box classifier. The results…
We propose an approach for explaining Bayesian network classifiers, which is based on compiling such classifiers into decision functions that have a tractable and symbolic form. We introduce two types of explanations for why a classifier may have classified an instance positively or negatively and suggest algorithms for computing these explanations. The first type of explanation identifies a minimal set of the currently active features that is responsible for the current classification, while the second type of explanation identifies a minimal set of features whose current state (active or not…
The paper introduces a novel framework for extracting model-agnostic human interpretable rules to explain a classifier's output. The human interpretable rule is defined as an axis-aligned hyper-cuboid containing the instance for which the classification decision has to be explained. The proposed procedure finds the largest (high \textit{coverage}) axis-aligned hyper-cuboid such that a high percentage of the instances in the hyper-cuboid have the same class label as the instance being explained (high \textit{precision}). Novel approximations to the coverage and precision measures in terms of th…
University of Toulouse（图卢兹大学）；Monash University（莫纳什大学）；IRIT（图卢兹信息学研究所）；CNRS（法国国家科学研究中心）
Recent work has shown that not only decision trees (DTs) may not be interpretable but also proposed a polynomial-time algorithm for computing one PI-explanation of a DT. This paper shows that for a wide range of classifiers, globally referred to as decision graphs, and which include decision trees and binary decision diagrams, but also their multi-valued variants, there exist polynomial-time algorithms for computing one PI-explanation. In addition, the paper also proposes a polynomial-time algorithm for computing one contrastive explanation. These novel algorithms build on explanation graphs (…
Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one. In this work, we propose LIME, a novel explanation technique that explains the predictions of any classifier in an interpretable and faithful manner, by lea…
Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）
An intrinsic time-scale decomposition (ITD) based method for power transformer fault diagnosis is proposed. Dissolved gas analysis (DGA) parameters are ranked according to their skewness, and then ITD based features extraction is performed. An optimal set of PRC features are determined by an XGBoost classifier. For classification purpose, an XGBoost classifier is used to the optimal PRC features set. The proposed method's performance in classification is studied using publicly available DGA data of 376 power transformers and employing an XGBoost classifier. The Proposed method achieves more th…
Classifier-Free Diffusion-Based Weakly-Supervised Approach for Health Indicator Derivation in Rotating Machines: Advancing Early Fault Detection and Condition Monitoring
University of Campinas（坎皮纳斯大学）；Leeds University Business School（利兹大学商学院）；COMSATS University Islamabad（伊斯兰堡COMSATS大学）
The use of algorithm-agnostic approaches is an emerging area of research for explaining the contribution of individual features towards the predicted outcome. Whilst there is a focus on explaining the prediction itself, a little has been done on explaining the robustness of these models, that is, how each feature contributes towards achieving that robustness. In this paper, we propose the use of Shapley values to explain the contribution of each feature towards the model's robustness, measured in terms of Receiver-operating Characteristics (ROC) curve and the Area under the ROC curve (AUC). Wi…
University of California, Berkeley（加州大学伯克利分校）；University of Chicago（芝加哥大学）
Intermediate-Severity (IS) faults present milder symptoms compared to severe faults, and are more difficult to detect and diagnose due to their close resemblance to normal operating conditions. The lack of IS fault examples in the training data can pose severe risks to Fault Detection and Diagnosis (FDD) methods that are built upon Machine Learning (ML) techniques, because these faults can be easily mistaken as normal operating conditions. Ensemble models are widely applied in ML and are considered promising methods for detecting out-of-distribution (OOD) data. We identify common pitfalls in t…
Uni. of Glasgow/Turing Institute（格拉斯哥大学/图灵研究所）；UCL/Turing Institute（伦敦大学学院/图灵研究所）；Amazon Tübingen（亚马逊图宾根）
We present a simple regularization of adversarial perturbations based upon the perceptual loss. While the resulting perturbations remain imperceptible to the human eye, they differ from existing adversarial perturbations in that they are semi-sparse alterations that highlight objects and regions of interest while leaving the background unaltered. As a semantically meaningful adverse perturbations, it forms a bridge between counterfactual explanations and adversarial perturbations in the space of images. We evaluate our approach on several standard explainability benchmarks, namely, weak locali…
Although interactive learning puts the user into the loop, the learner remains mostly a black box for the user. Understanding the reasons behind queries and predictions is important when assessing how the learner works and, in turn, trust. Consequently, we propose the novel framework of explanatory interactive learning: in each step, the learner explains its interactive query to the user, and she queries of any active classifier for visualizing explanations of the corresponding predictions. We demonstrate that this can boost the predictive and explanatory powers of and the trust into the learn…
In this study, the open-circuit faults diagnosis and location issue of the neutral-point-clamped (NPC) inverters are analysed. A novel fault diagnosis approach based on knowledge driven and data driven was presented for the open-circuit faults in insulated-gate bipolar transistors (IGBTs) of NPC inverter, and Concordia transform (knowledge driven) and random forests (RFs) technique (data driven) are employed to improve the robustness performance of the fault diagnosis classifier. First, the fault feature data of AC in either normal state or open-circuit faults states of NPC inverter are analys…
Perturbation-based explanation methods often measure the contribution of an input feature to an image classifier's outputs by heuristically removing it via e.g. blurring, adding noise, or graying out, which often produce unrealistic, out-of-samples. Instead, we propose to integrate a generative inpainter into three representative attribution methods to remove an input feature. Our proposed change improved all three methods in (1) generating more plausible counterfactual samples under the true data distribution; (2) being more accurate according to three metrics: object localization, deletion, …
Northeast Electric Power University（东北电力大学）；Technical University of Denmark（丹麦技术大学）
Three-phase PWM rectifiers are adopted extensively in industry because of their excellent properties and potential advantages. However, while the IGBT has an open-circuit fault, the system does not crash suddenly, the performance will be reduced for instance voltages fluctuation and current harmonics. A fault diagnosis method based on deep feedforward network with transient synthetic features is proposed to reduce the dependence on the fault mathematical models in this paper, which mainly uses the transient phase current to train the deep feedforward network classifier. Firstly, the features o…
Achieving a high prediction rate is a crucial task in fault detection. Although various classification procedures are available, none of them can give high accuracy in all applications. Therefore, in this paper, a novel multi-classifier fusion approach is developed to boost the performance of the individual classifiers. This is acquired by using Dempster-Shafer theory (DST). However, in cases with conflicting evidences, the DST may give counter-intuitive results. In this regard, a preprocessing technique based on a new metric is devised in order to measure and mitigate the conflict between the…
Random Forest (RFs) are among the most widely used Machine Learning (ML) classifiers. Even though RFs are not interpretable, there are no dedicated non-heuristic approaches for computing explanations of RFs. Moreover, there is recent work on polynomial algorithms for explaining ML models, including naive Bayes classifiers. Hence, one question is whether finding explanations of RFs can be solved in polynomial time. This paper answers this question negatively, by proving that computing one PI-explanation of an RF is D^P-complete. Furthermore, the paper proposes a propositional encoding for compu…
Avast Software（Avast软件公司）；Czech Technical University in Prague（布拉格捷克理工大学）
Learning from raw data input, thus limiting the need for feature engineering, is a component of many successful applications of machine learning methods in various domains. While many problems naturally translate into a vector representation directly usable in standard classifiers, a number of data sources have the natural form of structured data interchange formats (e.g., security logs in JSON/XML format). Existing methods, such as in Hierarchical Multiple Instance Learning (HMIL), allow learning from such data in their raw form. However, the explanation of the classifiers trained on raw stru…
Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希·赫兹研究所）；Technische Universität Berlin（柏林工业大学）；Korea University（高丽大学）
Layer-wise relevance propagation (LRP) is a recently proposed technique for explaining predictions of complex non-linear classifiers in terms of input variables. In this paper, we apply LRP for the first time to natural language processing (NLP). More precisely, we use it to explain the predictions of a convolutional neural network (CNN) trained on a topic categorization task. Our analysis highlights which words are relevant for a specific prediction of the CNN. We compare our technique to standard sensitivity analysis, both qualitatively and quantitatively, using a "word deleting" perturbatio…
ANITI, Université de Toulouse（图卢兹大学ANITI）；IRIT, Université de Toulouse III（图卢兹第三大学IRIT）；Monash University（莫纳什大学）；VMware Research（VMware研究）
Recent work proposed the computation of so-called PI-explanations of Naive Bayes Classifiers (NBCs). PI-explanations are subset-minimal sets of feature-value pairs that are sufficient for the prediction, and have been computed with state-of-the-art exact algorithms that are worst-case exponential in time and space. In contrast, we show that the computation of one PI-explanation for an NBC can be achieved in log-linear time, and that the same result also applies to the more general class of linear classifiers. Furthermore, we show that the enumeration of PI-explanations can be obtained with pol…
Time-frequency methods for vibration-based gearbox faults detection have been considered the most efficient method. Among these methods, continuous wavelet transform (CWT) as one of the best time-frequency method has been used for both stationary and transitory signals. Some deficiencies of CWT are problem of overlapping and distortion ofsignals. In this condition, a large amount of redundant information exists so that it may cause false alarm or misinterpretation of the operator. In this paper a modified method called Exact Wavelet Analysis is used to minimize the effects of overlapping and d…
Pacific Northwest National Laboratory（太平洋西北国家实验室）；University of Florida（佛罗里达大学）
Fault detection problem for closed loop uncertain dynamical systems, is investigated in this paper, using different deep learning based methods. Traditional classifier based method does not perform well, because of the inherent difficulty of detecting system level faults for closed loop dynamical system. Specifically, acting controller in any closed loop dynamical system, works to reduce the effect of system level faults. A novel Generative Adversarial based deep Autoencoder is designed to classify datasets under normal and faulty operating conditions. This proposed network performs significan…
Northeast Electric Power University（东北电力大学）；Technical University of Denmark（丹麦技术大学）
A fault diagnosis method for power electronics converters based on deep feedforward network and wavelet compression is proposed in this paper. The transient historical data after wavelet compression are used to realize the training of fault diagnosis classifier. Firstly, the correlation analysis of the voltage or current data running in various fault states is performed to remove the redundant features and the sampling point. Secondly, the wavelet transform is used to remove the redundant data of the features, and then the training sample data is greatly compressed. The deep feedforward networ…
Explaining Time Series Classifiers with PHAR: Rule Extraction and Fusion from Post-hoc Attributions
Jagiellonian Human-Centered AI Lab, Mark Kac Center for Complex Systems Research（杰克利昂人类中心人工智能实验室、马克·卡复杂系统研究中心）；Institute of Applied Computer Science, Jagiellonian University（应用计算机科学研究所、杰克利昂大学）
Faults in HVAC systems degrade thermal comfort and energy efficiency in buildings and have received significant attention from the research community, with data driven methods gaining in popularity. Yet the lack of labeled data, such as normal versus faulty operational status, has slowed the application of machine learning to HVAC systems. In addition, for any particular building, there may be an insufficient number of observed faults over a reasonable amount of time for training. To overcome these challenges, we present a transfer methodology for a novel Bayesian classifier designed to distin…
Bangladesh University of Engineering and Technology（孟加拉国工程技术大学）
In this paper, an Empirical Mode Decomposition-based method is proposed for the detection of transformer faults from Dissolve gas analysis (DGA) data. Ratio-based DGA parameters are ranked using their skewness. Optimal sets of intrinsic mode function coefficients are obtained from the ranked DGA parameters. A Hierarchical classification scheme employing XGBoost is presented for classifying the features to identify six different categories of transformer faults. Performance of the Proposed Method is studied for publicly available DGA data of 377 transformers. It is shown that the proposed metho…
Indian Institute of Information Technology Design and Manufacturing Jabalpur（印度信息技术设计与制造学院）；Birla Institute of Technology and Science – Pilani（比尔拉理工学院）；National Institute of Technology Karnataka（卡纳塔克国立理工学院）；VIT University（韦洛尔理工大学）
Gear drives are one of the most widely used transmission system in many machinery. Sound signals of a rotating machine contain the dynamic information about its health conditions. Not much information available in the literature reporting suitability of sound signals for fault diagnosis applications. Maximum numbers of literature are based on FFT (Fast Fourier Transform) analysis and have its own limitations with non-stationary signals like the ones from gears. In this paper, attempt has been made in using sound signals acquired from gears in good and simulated faulty conditions for the purpos…
University of Pennsylvania（宾夕法尼亚大学）；Apple Inc.（苹果公司）
There is a large literature explaining why AdaBoost is a successful classifier. The literature on AdaBoost focuses on classifier margins and boosting's interpretation as the optimization of an exponential likelihood function. These existing explanations, however, have been pointed out to be incomplete. A random forest is another popular ensemble method for which there is substantially less explanation in the literature. We introduce a novel perspective on AdaBoost and random forests that proposes that the two algorithms work for similar reasons. While both classifiers achieve similar predictiv…
This paper aims at improving the classification accuracy of a Support Vector Machine (SVM) classifier with Sequential Minimal Optimization (SMO) training algorithm in order to properly classify failure and normal instances from oil and gas equipment data. Recent applications of failure analysis have made use of the SVM technique without implementing SMO training algorithm, while in our study we show that the proposed solution can perform much better when using the SMO training algorithm. Furthermore, we implement the ensemble approach, which is a hybrid rule based and neural network classifier…
Much effort has been devoted to understanding the decisions of deep neural networks in recent years. A number of model-aware saliency methods were proposed to explain individual classification decisions by creating saliency maps. However, they are not applicable when the parameters and the gradients of the underlying models are unavailable. Recently, model-agnostic methods have also received attention. As one of them, \textit{Prediction Difference Analysis} (PDA), a probabilistic sound methodology, was proposed. In this work, we first show that PDA can suffer from saturated classifiers. The sa…
Lenovo Research（联想研究院）；University of Chinese Academy of Sciences（中国科学院大学）
Despite outstanding contribution to the significant progress of Artificial Intelligence (AI), deep learning models remain mostly black boxes, which are extremely weak in explainability of the reasoning process and prediction results. Explainability is not only a gateway between AI and society but also a powerful tool to detect flaws in the model and biases in the data. Local Interpretable Model-agnostic Explanation (LIME) is a recent approach that uses an interpretable model to form a local explanation for the individual prediction result. The current implementation of LIME adopts the linear r…
Fault detection and diagnosis for the engine electrical system of a space launcher based on a temporal convolutional autoencoder and calibrated classifiers
Deep neural networks are powerful statistical learners. However, their predictions do not come with an explanation of their process. To analyze these models, explanation methods are being developed. We present a novel explanation method, called OLM, for natural language processing classifiers. This method combines occlusion and language modeling, which are techniques central to explainability and NLP, respectively. OLM gives explanations that are theoretically sound and easy to understand. We make several contributions to the theory of explanation methods. Axioms for explanation methods are an…
TU Kaiserslautern（凯泽斯劳滕工业大学）；German Research Center for Artificial Intelligence GmbH (DFKI)（德国人工智能研究中心）
Human-centric explainability of AI-based Decision Support Systems (DSS) using visual input modalities is directly related to reliability and practicality of such algorithms. An otherwise accurate and robust DSS might not enjoy trust of experts in critical application areas if it is not able to provide reasonable justification of its predictions. This paper introduces Concept Localization Maps (CLMs), which is a novel approach towards explainable image classifiers employed as DSS. CLMs extend Concept Activation Vectors (CAVs) by locating significant regions corresponding to a learned concept in…
timeXplain -- A Framework for Explaining the Predictions of Time Series Classifiers
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Hasso Plattner Institute, University of Potsdam（波茨坦大学哈索·普拉特纳研究所）；Faculty of Computer Science, University of Vienna（维也纳大学计算机学院）；Humboldt University of Berlin（柏林洪堡大学）
How can we understand classification decisions made by deep neural networks? Many existing explainability methods rely solely on correlations and fail to account for confounding, which may result in potentially misleading explanations. To overcome this problem, we define the Causal Concept Effect (CaCE) as the causal effect of (the presence or absence of) a human-interpretable concept on a deep neural net's predictions. We show that the CaCE measure can avoid errors stemming from confounding. Estimating CaCE is difficult in situations where we cannot easily simulate the do-operator. To mitigat…
University of Liechtenstein（列支敦士登大学）；University of Lausanne（洛桑大学）
Interpreting a large number of neurons in deep learning is difficult. Our proposed `CLAssifier-DECoder' architecture (ClaDec) facilitates the understanding of the output of an arbitrary layer of neurons or subsets thereof. It uses a decoder that transforms the incomprehensible representation of the given neurons to a representation that is more similar to the domain a human is familiar with. In an image recognition problem, one can recognize what information (or concepts) a layer maintains by contrasting reconstructed images of ClaDec with those of a conventional auto-encoder(AE) serving as re…
Freie Universität Berlin（柏林自由大学）；University of Southern Denmark（南丹麦大学）；Universität der Bundeswehr München（慕尼黑联邦国防军大学）
The importance of neighborhood construction in local explanation methods has been already highlighted in the literature. And several attempts have been made to improve neighborhood quality for high-dimensional data, for example, texts, by adopting generative models. Although the generators produce more realistic samples, the intuitive sampling approaches in the existing solutions leave the latent space underexplored. To overcome this problem, our work, focusing on local model-agnostic explanations for text classifiers, proposes a progressive approximation approach that refines the neighborhood…
Inspired by recent progress in machine learning, a data-driven fault diagnosis and isolation (FDI) scheme is explicitly developed for failure in the fuel supply system and sensor measurements of the laboratory gas turbine system. A passive approach of fault diagnosis is implemented where a model is trained using machine learning classifiers to detect a given set of fault scenarios in real-time on which it is trained. Towards the end, a comparative study is presented for well-known classification techniques, namely Support vector classifier, linear discriminant analysis, K-neighbor, and decisio…
