检索结果-内蒙古大学图书馆

Finding the right XAI method - A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate science

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bommer, Philine Kretschmer, Marlene Hedström, Anna Bareeva, Dilyara Höhne, Marina M.-C. Department of Machine Learning Technische Universität Berlin Berlin10587 Germany Understandable Machine Intelligence Lab Department of Data Science ATB Potsdam14469 Germany Institute for Meteorology University of Leipzig Leipzig Germany Department of Meteorology University of Reading Reading United Kingdom BIFOLD - Berlin Institute for the Foundations of Learning and Data Berlin10587 Germany Machine Learning Group UiT the Arctic University of Norway Tromso9037 Norway Department of Computer Science University of Potsdam Potsdam14476 Germany

Explainable artificial intelligence (XAI) methods shed light on the predictions of machine learning algorithms. Several different approaches exist and have already been applied in climate science. However, usually missing ground truth explanations complicate their evaluation and comparison, subsequently impeding the choice of the XAI method. Therefore, in this work, we introduce XAI evaluation in the climate context and discuss different desired explanation properties, namely robustness, faithfulness, randomization, complexity, and localization. To this end, we chose previous work as a case study where the decade of annual-mean temperature maps is predicted. After training both a multi-layer perceptron (MLP) and a convolutional neural network (CNN), multiple XAI methods are applied and their skill scores in reference to a random uniform explanation are calculated for each property. Independent of the network, we find that XAI methods Integrated Gradients, layer-wise relevance propagation, and input times gradients exhibit considerable robustness, faithfulness, and complexity while sacrificing randomization performance. Sensitivity methods - gradient, SmoothGrad, NoiseGrad, and FusionGrad, match the robustness skill but sacrifice faithfulness and complexity for randomization skill. We find architecturedependent performance differences regarding robustness, complexity and localization skills of different XAI methods, highlighting the necessity for research task-specific evaluation. Overall, our work offers an overview of different evaluation properties in the climate science context and shows how to compare and benchmark different explanation methods, assessing their suitability based on strengths and weaknesses, for the specific research problem at hand. By that, we aim to support climate researchers in the selection of a suitable XAI method. © 2023, CC BY.

关键词： Multilayer neural networks

MINI-Net: Multiple instance ranking network for video highlight detection

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Hong, Fa-Ting Huang, Xuanteng Li, Wei-Hong Zheng, Wei-Shi School of Data and Computer Science Sun Yat-sen University China Peng Cheng Laboratory Shenzhen518005 China VICO Group University of Edinburgh United Kingdom Pazhou Lab Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

We address the weakly supervised video highlight detection problem for learning to detect segments that are more attractive in training videos given their video event label but without expensive supervision of manually annotating highlight segments. While manually averting localizing highlight segments, weakly supervised modeling is challenging, as a video in our daily life could contain highlight segments with multiple event types, e.g., skiing and surfing. In this work, we propose casting weakly supervised video highlight detection modeling for a given specific event as a multiple instance ranking network (MINI-Net) learning. We consider each video as a bag of segments, and therefore, the proposed MINI-Net learns to enforce a higher highlight score for a positive bag that contains highlight segments of a specific event than those for negative bags that are irrelevant. In particular, we form a max-max ranking loss to acquire a reliable relative comparison between the most likely positive segment instance and the hardest negative segment instance. With this max-max ranking loss, our MINI-Net effectively leverages all segment information to acquire a more distinct video feature representation for localizing the highlight segments of a specific event in a video. The extensive experimental results on three challenging public benchmarks clearly validate the efficacy of our multiple instance ranking approach for solving the problem. Copyright © 2020, The Authors. All rights reserved.

关键词： machine learning

Leveraging Unlabeled data for 3D Medical Image Segmentation Through Self-Supervised Contrastive Learning

学校读者我要写书评

暂无评论

Leveraging Unlabeled Data for 3D Medical Image Segmentation ...

IEEE International Symposium on Biomedical Imaging

作者： Sanaz Karimijafarbigloo Reza Azad Yury Velichko Ulas Bagci Dorit Merhof Faculty of Informatics and Data Science University of Regensburg Germany Faculty of Electrical Engineering and Information Technology RWTH Aachen University Germany Machine and Hybrid Intelligence Lab Northwestern University Chicago IL USA Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Current 3D semi-supervised segmentation methods face significant challenges such as limited consideration of contextual information and the inability to generate reliable pseudo-labels for effective unsupervised data use. To address these challenges, we introduce two distinct subnetworks designed to explore and exploit the discrepancies between them, ultimately correcting the erroneous prediction results. More specifically, we identify regions of inconsistent predictions and initiate a targeted verification training process. This procedure strategically fine-tunes and harmonizes the predictions of the subnetworks, leading to enhanced utilization of contextual information. Furthermore, to adaptively fine-tune the network’s representational capacity and reduce prediction uncertainty, we employ a self-supervised contrastive learning paradigm. For this, we use the network’s confidence to distinguish between reliable and unreliable predictions. The model is then trained to effectively minimize unreliable predictions. Our experimental results for organ segmentation, obtained from clinical MRI and CT scans, demonstrate the effectiveness of our approach when compared to state-of-the-art methods. The codebase is accessible on GitHub.

关键词： Training Three-dimensional displays Uncertainty Magnetic resonance imaging Computed tomography Semantic segmentation Contrastive learning

Refining BERT embeddings for document hashing via mutual information maximization

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ou, Zijing Su, Qinliang Yu, Jianxing Zhao, Ruihui Zheng, Yefeng Liu, Bang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Artificial Intelligence Sun Yat-sen University Guangdong China Tencent Jarvis Lab Rali & Mila Université de Montréal Guangdong Key Lab. of Big Data Analysis and Processing Guangzhou China Key Lab. of Machine Intelligence and Advanced Computing Ministry of Education China

Existing unsupervised document hashing methods are mostly established on generative models. Due to the difficulties of capturing long dependency structures, these methods rarely model the raw documents directly, but instead to model the features extracted from them (e.g. bag-of-words (BOW), TFIDF). In this paper, we propose to learn hash codes from BERT embeddings after observing their tremendous successes on downstream tasks. As a first try, we modify existing generative hashing models to accommodate the BERT embeddings. However, little improvement is observed over the codes learned from the old BOW or TFIDF features. We attribute this to the reconstruction requirement in the generative hashing, which will enforce irrelevant information that is abundant in the BERT embeddings also compressed into the codes. To remedy this issue, a new unsupervised hashing paradigm is further proposed based on the mutual information (MI) maximization principle. Specifically, the method first constructs appropriate global and local codes from the documents and then seeks to maximize their mutual information. Experimental results on three benchmark datasets demonstrate that the proposed method is able to generate hash codes that outperform existing ones learned from BOW features by a substantial margin. Copyright © 2021, The Authors. All rights reserved.

关键词： Embeddings

Gray Learning from Non-IID data with Out-of-distribution Samples

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhao, Zhilin Cao, Longbing Wang, Chang-Dong The Data Science Lab School of Computing and DataX Research Centre Macquarie University SydneyNSW2109 Australia The School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Computational Science Guangzhou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The integrity of training data, even when annotated by experts, is far from guaranteed, especially for non-IID datasets comprising both in- and out-of-distribution samples. In an ideal scenario, the majority of samples would be in-distribution, while samples that deviate semantically would be identified as out-of-distribution and excluded during the annotation process. However, experts may erroneously classify these out-of-distribution samples as in-distribution, assigning them labels that are inherently unreliable. This mixture of unreliable labels and varied data types makes the task of learning robust neural networks notably challenging. We observe that both in- and out-of-distribution samples can almost invariably be ruled out from belonging to certain classes, aside from those corresponding to unreliable ground-truth labels. This opens the possibility of utilizing reliable complementary labels that indicate the classes to which a sample does not belong. Guided by this insight, we introduce a novel approach, termed Gray Learning (GL), which leverages both ground-truth and complementary labels. Crucially, GL adaptively adjusts the loss weights for these two label types based on prediction confidence levels. By grounding our approach in statistical learning theory, we derive bounds for the generalization error, demonstrating that GL achieves tight constraints even in non-IID settings. Extensive experimental evaluations reveal that our method significantly outperforms alternative approaches grounded in robust statistics. Copyright © 2022, The Authors. All rights reserved.

关键词： machine learning

Solar Energy Forecasting With Fuzzy Time Series Using High-Order Fuzzy Cognitive Maps

学校读者我要写书评

暂无评论

Solar Energy Forecasting With Fuzzy Time Series Using High-O...

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Omid Orang Rodrigo Silva Petrônio Cândido de Lima e Silva Frederico Gadelha Guimarães Machine Intelligence and Data Science (MINDS) Lab Universidade Federal de Minas Gerais UFMG Belo Horizonte Brazil Department of Computer Science Universidade Federal de Ouro Preto UFOP Ouro Preto Brazil Instituto Federal do Norte de Minas Gerais IFNMG Januaria Brazil

ISBN: (数字)9781728169323

ISBN: (纸本)9781728169330

Various studies indicate that Fuzzy Time Series (FTS) methods can obtain high accuracy in a variety of forecasting applciations. However, weighted FTS methods tend to show superiority in contrast to weightless ones. This study exploits the use of Fuzzy Cognitive Map (FCM) technique to generate the rules in the knowledge base for the FTS forecasting method. The proposed hybrid method, named HFCM-FTS, combines High Order Fuzzy Cognitive Maps (HFCM) and High Order Fuzzy Time Series (HOFTS), where the weight matrices associated with the state transitions are learned via the genetic algorithm from the data. The objective of FCM is to find the weight matrices that model the causal relations among the concepts defined in the Universe of Discourse. As a case study, we consider solar energy forecasting with public data for Brazilian solar stations from the year 2012 to 2015. The proposed HFCM-FTS is compared with HOFTS, Weighted High Order FTS (WHOFTS), and Probabilistic Weighted FTS (PWFTS) methods. The experiments also cover the influence of three modeling elements on the accuracy of the presented model including the number of concepts, activation function, and bias. The results show that the HFCM-FTS is able to achieve the best results with a low number of concepts.

关键词： Time series analysis Forecasting Predictive models Fuzzy sets Fuzzy cognitive maps Genetic algorithms Linguistics

Mixing Histopathology Prototypes into Robust Slide-Level Representations for Cancer Subtyping

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Butke, Joshua Hashimoto, Noriaki Takeuchi, Ichiro Miyoshi, Hiroaki Ohshima, Koichi Sakuma, Jun Machine Learning and Data Mining Lab University of Tsukuba Japan RIKEN Center for Advanced Intelligence Project Japan Department of Mechanical Systems Engineering Nagoya University Japan Department of Pathology Kurume University Japan Department of Computer Science Tokyo Institute of Technology Japan

Whole-slide image analysis via the means of computational pathology often relies on processing tessellated gigapixel images with only slide-level labels available. Applying multiple instance learning-based methods or transformer models is computationally expensive as, for each image, all instances have to be processed simultaneously. The MLP-Mixer is an under-explored alternative model to common vision transformers, especially for large-scale datasets. Due to the lack of a self-attention mechanism, they have linear computational complexity to the number of input patches but achieve comparable performance on natural image datasets. We propose a combination of feature embedding and clustering to preprocess the full whole-slide image into a reduced prototype representation which can then serve as input to a suitable MLP-Mixer architecture. Our experiments on two public benchmarks and one inhouse malignant lymphoma dataset show comparable performance to current state-of-the-art methods, while achieving lower training costs in terms of computational time and memory load. Code is publicly available at https://***/butkej/ProtoMixer. Copyright © 2023, The Authors. All rights reserved.

关键词： Mixers (machinery)

Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hedström, Anna Weber, Leander Bareeva, Dilyara Krakowczyk, Daniel Motzkus, Franz Samek, Wojciech Lapuschkin, Sebastian Höhne, Marina M.-C. Understandable Machine Intelligence Lab TU Berlin Berlin10587 Germany Department of Electrical Engineering and Computer Science TU Berlin Berlin10587 Germany Department of Artificial Intelligence Fraunhofer Heinrich-Hertz-Institute Berlin10587 Germany Department of Computer Science University of Potsdam Potsdam14476 Germany BIFOLD - Berlin Institute for the Foundations of Learning and Data Berlin10587 Germany

The evaluation of explanation methods is a research topic that has not yet been explored deeply, however, since explainability is supposed to strengthen trust in artificial intelligence, it is necessary to systematically review and compare explanation methods in order to confirm their correctness. Until now, no tool with focus on XAI evaluation exists that exhaustively and speedily allows researchers to evaluate the performance of explanations of neural network predictions. To increase transparency and reproducibility in the field, we therefore built Quantus-a comprehensive, evaluation toolkit in Python that includes a growing, wellorganised collection of evaluation metrics and tutorials for evaluating explainable methods. The toolkit has been thoroughly tested and is available under an open-source license on PyPi (or on https://***/understandable-machine-intelligence-lab/Quantus/). © 2022, CC BY-NC-SA.

关键词： Python

Topology-Preserving Automatic labeling of Coronary Arteries via Anatomy-aware Connection Classifier

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Zhixing Zhao, Ziwei Wang, Dong Zhao, Shishuang Liu, Yuhang Liu, Jia Wang, Liwei Center for Data Science Peking University Beijing China National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University Beijing China Yizhun Medical AI Co. Ltd Beijing China Peking University First Hospital Beijing China Center for Machine Learning Research Peking University Beijing China Pazhou Lab Guangzhou China

Automatic labeling of coronary arteries is an essential task in the practical diagnosis process of cardiovascular diseases. For experienced radiologists, the anatomically predetermined connections are important for labeling the artery segments accurately, while this prior knowledge is barely explored in previous studies. In this paper, we present a new framework called Topolab which incorporates the anatomical connections into the network design explicitly. Specifically, the strategies of intra-segment feature aggregation and inter-segment feature interaction are introduced for hierarchical segment feature extraction. Moreover, we propose the anatomy-aware connection classifier to enable classification for each connected segment pair, which effectively exploits the prior topology among the arteries with different categories. To validate the effectiveness of our method, we contribute high-quality annotations of artery labeling to the public orCaScore dataset. The experimental results on both the orCaScore dataset and an in-house dataset show that our Topolab has achieved state-of-the-art performance. © 2023, CC BY.

关键词： Topology