The practical application of deep neural networks are still limited by their lack of transparency. One of the efforts to provide explanation for decisions made by artificial intelligence (AI) is the use of saliency or heat maps highlighting relevant regions that contribute significantly to its prediction. A layer-wise amplitude filtering method was previously introduced to improve the quality of heatmaps, performing error corrections by noise-spike suppression. In this study, we generalize the layerwise error correction by considering any identifiable error and assuming there exists a groundtruth interpretable information. The forms of errors propagated through layerwise relevance methods are studied and we propose a filtering technique for interpretability signal rectification taylored to the trend of signal amplitude of the particular neural network used. Finally, we put forth arguments for the use of groundtruth interpretable information.
LIRIS - UMR 5205 CNRS（法国国家科学研究中心LIRIS联合研究单位5205）；Ecole Centrale de Lyon（里昂中央理工学院）；LVMH Recherche - Parfums et cosmetiques（路威酩轩香水化妆品研究中心）
The lack of transparency of neural networks stays a major break for their use. The Layerwise Relevance Propagation technique builds heat-maps representing the relevance of each input in the model s decision. The relevance spreads backward from the last to the first layer of the Deep Neural Network. Layer-wise Relevance Propagation does not manage normalization layers, in this work we suggest a method to include normalization layers. Specifically, we build an equivalent network fusing normalization layers and convolutional or fully connected layers. Heatmaps obtained with our method on MNIST an…
Methodological Explainability Evaluation of an Interpretable Deep Learning Model for Post-Hepatectomy Liver Failure Prediction Incorporating Counterfactual Explanations and Layerwise Relevance Propagation: A Prospective In Silico Trial
Maastricht University（马斯特里赫特大学）；Maastricht University Medical Center+（马斯特里赫特大学医学中心+）；The First Affiliated Hospital of Sun Yat-sen University（中山大学附属第一医院）；Guizhou University（贵州大学）；Université Libre de Bruxelles（布鲁塞尔自由大学）
Ghent University（根特大学）；University of Edinburgh（爱丁堡大学）
Even though deep neural networks (DNNs) achieve state-of-the-art results for a number of problems involving genomic data, getting DNNs to explain their decision-making process has been a major challenge due to their black-box nature. One way to get DNNs to explain their reasoning for prediction is via attribution methods which are assumed to highlight the parts of the input that contribute to the prediction the most. Given the existence of numerous attribution methods and a lack of quantitative results on the fidelity of those methods, selection of an attribution method for sequence-based task…
Semantic-Aware Gaussian Process Calibration with Structured Layerwise Kernels for Deep Neural Networks
Next Generation Defence Multidisciplinary Technology Research Center, Pohang University of Science and Technology（下一代国防多学科技术研究中心，POSTECH大学）；Department of Electrical Engineering, Pohang University of Science and Technology（电气工程系，POSTECH大学）
Deep neural networks excel at comprehending complex visual signals, delivering on par or even superior performance to that of human experts. However, ad-hoc visual explanations of model decisions often reveal an alarming level of reliance on exploiting non-causal visual cues that strongly correlate with the target label in training data. As such, deep neural nets suffer compromised generalization to novel inputs collected from different sources, and the reverse engineering of their decision rules offers limited interpretability. To overcome these limitations, we present a novel contrastive lea…
Mutual Information (MI) based feature selection makes use of MI to evaluate each feature and eventually shortlists a relevant feature subset, in order to address issues associated with high-dimensional datasets. Despite the effectiveness of MI in feature selection, we notice that many state-of-the-art algorithms disregard the so-called unique relevance (UR) of features, and arrive at a suboptimal selected feature subset which contains a non-negligible number of redundant features. We point out that the heart of the problem is that all these MIBFS algorithms follow the criterion of Maximize Rel…
Wuhan University（武汉大学）；City University of Hong Kong（香港城市大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Tencent AI Lab（腾讯人工智能实验室）
In this paper, we propose a novel Convolutional Neural Network (CNN) structure for general-purpose multi-task learning (MTL), which enables automatic feature fusing at every layer from different tasks. This is in contrast with the most widely used MTL CNN structures which empirically or heuristically share features on some specific layers (e.g., share all the features except the last convolutional layer). The proposed layerwise feature fusing scheme is formulated by combining existing CNN components in a novel way, with clear mathematical interpretability as discriminative dimensionality reduc…
Colorado State University（科罗拉多州立大学）；Cooperative Institute for Research in the Atmosphere（大气研究合作研究所）
Neural networks have become increasingly prevalent within the geosciences, although a common limitation of their usage has been a lack of methods to interpret what the networks learn and how they make decisions. As such, neural networks have often been used within the geosciences to most accurately identify a desired output given a set of inputs, with the interpretation of what the network learns used as a secondary metric to ensure the network is making the right decision for the right reason. Neural network interpretation techniques have become more advanced in recent years, however, and we …
AudioMNIST: Exploring Explainable Artificial Intelligence for Audio Analysis on a Simple Benchmark
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）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（BIFOLD——柏林学习与数据基础研究所）
EXplainable AI (XAI) methods have been proposed to interpret how a deep neural network predicts inputs through model saliency explanations that highlight the parts of the inputs deemed important to arrive a decision at a specific target. However, it remains challenging to quantify correctness of their interpretability as current evaluation approaches either require subjective input from humans or incur high computation cost with automated evaluation. In this paper, we propose backdoor trigger patterns--hidden malicious functionalities that cause misclassification--to automate the evaluation of…
Deep learning techniques have been successfully deployed for automating plant stress identification and quantification. In recent years, there is a growing push towards training models that are interpretable -i.e. that justify their classification decisions by visually highlighting image features that were crucial for classification decisions. The expectation is that trained network models utilize image features that mimic visual cues used by plant pathologists. In this work, we compare some of the most popular interpretability methods: Saliency Maps, SmoothGrad, Guided Backpropogation, Deep T…
GFSR-Net: Guided Focus via Segment-Wise Relevance Network for Interpretable Deep Learning in Medical Imaging
Institute of Physical Chemistry (IPC) and Abbe Center of Photonics (ACP), Friedrich Schiller University Jena（耶拿弗里德里希·席勒大学物理化学研究所与阿贝光子学中心）；Leibniz Institute of Photonic Technology（莱布尼茨光子技术研究所）
SHAMSUL: Systematic Holistic Analysis to investigate Medical Significance Utilizing Local interpretability methods in deep learning for chest radiography pathology prediction
Stockholm University（斯德哥尔摩大学）；Skatturinn (Iceland Revenue and Customs)（冰岛税务总局（冰岛税收和海关局））
Convolutional Neural Networks (CNN) have become state-of-the-art in the field of image classification. However, not everything is understood about their inner representations. This paper tackles the interpretability and explainability of the predictions of CNNs for multi-class classification problems. Specifically, we propose a novel visualization method of pixel-wise input attribution called Softmax-Gradient Layer-wise Relevance Propagation (SGLRP). The proposed model is a class discriminate extension to Deep Taylor Decomposition (DTD) using the gradient of softmax to back propagate the relev…
Linear classifier probes are frequently utilized to better understand how neural networks function. Researchers have approached the problem of determining unit importance in neural networks by probing their learned, internal representations. Linear classifier probes identify highly selective units as the most important for network function. Whether or not a network actually relies on high selectivity units can be tested by removing them from the network using ablation. Surprisingly, when highly selective units are ablated they only produce small performance deficits, and even then only in some…
CountXplain: Interpretable Cell Counting with Prototype-Based Density Map Estimation
Department of Computer Science, Iowa State University（计算机科学系，爱荷华州立大学）；Department of Genetics, Development, and Cell Biology, Iowa State University（遗传学、发育与细胞生物学系，爱荷华州立大学）；Molecular, Cellular, and Developmental Biology Program, Iowa State University（分子、细胞与发育生物学项目，爱荷华州立大学）；Neuroscience Program, Iowa State University（神经科学项目，爱荷华州立大学）；Nanovaccine Institute, Iowa State University（纳米疫苗研究所，爱荷华州立大学）
Technical University of Munich（慕尼黑工业大学）；Sharif University of Technology（谢里夫理工大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
Interpretability in Graph Convolutional Networks (GCNs) has been explored to some extent in computer vision in general, yet, in the medical domain, it requires further examination. Moreover, most of the interpretability approaches for GCNs, especially in the medical domain, focus on interpreting the model in a post hoc fashion. In this paper, we propose an interpretable graph learning-based model which 1) interprets the clinical relevance of the input features towards the task, 2) uses the explanation to improve the model performance and, 3) learns a population level latent graph that may be u…
Learning Visually Interpretable Oscillator Networks for Soft Continuum Robots from Video
Department of Advanced Interdisciplinary Studies, The University of Tokyo（东京大学先进跨学科研究系）；Institute of Assembly Technology and Robotics, Leibniz University Hannover（莱比锡大学汉诺威装配技术与机器人研究所）；Research Center for Advanced Science and Technology, The University of Tokyo（东京大学先进科学研究中心）
