Recurrence-Aware Long-Term Cognitive Network for Explainable Pattern Classification
Tilburg University（蒂尔堡大学）；Universidad de Talca（塔尔卡大学）；Eindhoven University of Technology（埃因霍温理工大学）；Vrije Universiteit Brussel（布鲁塞尔自由大学）；University of Miami（迈阿密大学）
Gonzalo Nápoles, Yamisleydi Salgueiro, Isel Grau, Maikel Leon Espinosa
Machine learning solutions for pattern classification problems are nowadays widely deployed in society and industry. However, the lack of transparency and accountability of most accurate models often hinders their safe use. Thus, there is a clear need for developing explainable artificial intelligence mechanisms. There exist model-agnostic methods that summarize feature contributions, but their interpretability is limited to predictions made by black-box models. An open challenge is to develop models that have intrinsic interpretability and produce their own explanations, even for classes of models that are traditionally considered black boxes like (recurrent) neural networks. In this paper, we propose a Long-Term Cognitive Network for interpretable pattern classification of structured data. Our method brings its own mechanism for providing explanations by quantifying the relevance of each feature in the decision process. For supporting the interpretability without affecting the performance, the model incorporates more flexibility through a quasi-nonlinear reasoning rule that allows controlling nonlinearity. Besides, we propose a recurrence-aware decision model that evades the issues posed by the unique fixed point while introducing a deterministic learning algorithm to compute the tunable parameters. The simulations show that our interpretable model obtains competitive results when compared to state-of-the-art white and black-box models.
Google（谷歌）；The George Washington University（乔治华盛顿大学）
The need for explainable AI (XAI) is well established but relatively little has been published outside of the supervised learning paradigm. This paper focuses on a principled approach to applying explainability and interpretability to the task of unsupervised anomaly detection. We argue that explainability is principally an algorithmic task and interpretability is principally a cognitive task, and draw on insights from the cognitive sciences to propose a general-purpose method for practical diagnosis using explained anomalies. We define Attribution Error, and demonstrate, using real-world labe…
Deep Learning Approaches with Explainable AI for Differentiating Alzheimer Disease and Mild Cognitive Impairment
School of Mathematical and Natural Sciences（数学与自然科学学院）；Arizona State University（亚利桑那州立大学）；Department of Mathematics（数学系）；Florida Gulf Coast University（佛罗里达海岸大学）；Department of Public Health（公共卫生系）；Julia Jones Matthews School of Population and Public Health（朱莉亚·琼斯·马修斯人口与公共卫生学院）；Texas Tech University Health Sciences Center（德克萨斯农工大学健康科学中心）
The shape of the brain's connections is predictive of cognitive performance: an explainable machine learning study
Harvard Medical School（哈佛医学院）；Brigham and Women’s Hospital（布莱根妇女医院）；Massachusetts General Hospital（麻省总医院）；The University of Sydney（悉尼大学）；Beijing Institute of Technology（北京理工大学）；Boston University（波士顿大学）；University of Electronic Science and Technology of China（电子科技大学）；Harvard University（哈佛大学）；Harvard-MIT Health Sciences and Technology（哈佛-麻省理工健康科学与技术学部）
Deep multimodal saliency parcellation of cerebellar pathways: linking microstructure and individual function through explainable multitask learning
University of New South Wales（新南威尔士大学）；Brigham and Women’s Hospital, Harvard Medical School（哈佛医学院布莱根妇女医院）；Harvard University（哈佛大学）；Massachusetts General Hospital, Harvard Medical School（哈佛医学院麻省总医院）；Boston University School of Medicine（波士顿大学医学院）；University of Electronic Science and Technology of China（电子科技大学）；Colby College（科尔比学院）
Mila - Quebec AI Institute（Mila-魁北克人工智能研究所）；Université de Montréal（蒙特利尔大学）
Attention and self-attention mechanisms, are now central to state-of-the-art deep learning on sequential tasks. However, most recent progress hinges on heuristic approaches with limited understanding of attention's role in model optimization and computation, and rely on considerable memory and computational resources that scale poorly. In this work, we present a formal analysis of how self-attention affects gradient propagation in recurrent networks, and prove that it mitigates the problem of vanishing gradients when trying to capture long-term dependencies by establishing concrete bounds for …
An explainable framework for the relationship between dementia and glucose metabolism patterns
Department of Signal Processing and Biomedical Applications, University of Granada（信号处理与生物医学应用系，格拉纳达大学）；Department of Statistics and Operations Research, University of Valencia（统计与运筹学系，瓦伦西亚大学）；Department of Communication Engineering, University of Malaga（通信工程系，马拉加大学）
Explainable Graph Neural Networks: Understanding Brain Connectivity and Biomarkers in Dementia
School of Computing Technologies RMIT University Melbourne VIC Australia；Department of Biological Sciences；Department of Computer Science \& Information Systems Birla Institute of Technology；Institute of Innovation, Science；Sustainability Federation University Australia Ballarat VIC Australia；RMIT University；Birla Institute of Technology；Federation University Australia
Training graph classifiers able to distinguish between healthy brains and dysfunctional ones, can help identifying substructures associated to specific cognitive phenotypes. However, the mere predictive power of the graph classifier is of limited interest to the neuroscientists, which have plenty of tools for the diagnosis of specific mental disorders. What matters is the interpretation of the model, as it can provide novel insights and new hypotheses. In this paper we propose \emph{counterfactual graphs} as a way to produce local post-hoc explanations of any black-box graph classifier. Given …
Deconstructing Recurrence, Attention, and Gating: Investigating the transferability of Transformers and Gated Recurrent Neural Networks in forecasting of dynamical systems
School of Engineering and Applied Sciences, Harvard University（哈佛大学工程与应用科学学院）；Institute of Structural Engineering, ETH Zurich（苏黎世联邦理工学院结构工程研究所）
University at Buffalo, State University of New York（纽约州立大学布法罗分校）；University of Oregon（俄勒冈大学）
A framework is presented to extract and understand decision-making information from a deep neural network (DNN) classifier of jet substructure tagging techniques. The general method studied is to provide expert variables that augment inputs ("eXpert AUGmented" variables, or XAUG variables), then apply layerwise relevance propagation (LRP) to networks both with and without XAUG variables. The XAUG variables are concatenated with the intermediate layers after network-specific operations (such as convolution or recurrence), and used in the final layers of the network. The results of comparing net…
Cognitive Networks and Performance Drive fMRI-Based State Classification Using DNN Models
D-Prime LLC（D-Prime有限责任公司）；US DEVCOM Army Research Laboratory（美国DEVCOM陆军研究实验室）；University of Maryland, Baltimore County（马里兰大学巴尔的摩郡分校）；Tanzen Medical Inc.（Tanzen医疗公司）
sMRI-PatchNet: A novel explainable patch-based deep learning network for Alzheimer's disease diagnosis and discriminative atrophy localisation with Structural MRI
Manchester Metropolitan University（曼彻斯特城市大学）；Brunel University（布鲁内尔大学）；University of Sheffield（谢菲尔德大学）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
A computational framework for longitudinal medication adherence prediction in breast cancer survivors: A social cognitive theory based approach
Department of Systems and Information Engineering, University of Virginia（弗吉尼亚大学系统与信息工程系）；SDSU/UC San Diego Joint Doctoral Program in Clinical Psychology（圣地亚哥州立大学/加州大学圣地亚哥分校临床心理学联合博士项目）；Department of Computer Science, The University of Alabama（阿拉巴马大学计算机科学系）；Department of Psychology, San Diego State University（圣地亚哥州立大学心理学系）
