检索结果-内蒙古大学图书馆

A THEORY OF INITIALISATION’S IMPACT ON SPECIALISATION

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Jarvis, Devon Lee, Sebastian Dominé, Clémentine Carla Juliette Saxe, Andrew M. Mannelli, Stefano Sarao School of Computer Science and Applied Mathematics University of the Witwatersrand South Africa Center for Computational Neuroscience Flatiron Institute Simons Foundation Gatsby Computational Neuroscience Unit Sainsbury Wellcome Centre UCL United Kingdom Data Science and AI Computer Science and Engineering Chalmers University of Technology University of Gothenburg Sweden Machine Intelligence and Neural Discovery Institute University of the Witwatersrand South Africa CIFAR Azrieli Global Scholar CIFAR

Prior work has demonstrated a consistent tendency in neural networks engaged in continual learning tasks, wherein intermediate task similarity results in the highest levels of catastrophic interference. This phenomenon is attributed to the network’s tendency to reuse learned features across tasks. However, this explanation heavily relies on the premise that neuron specialisation occurs, i.e. the emergence of localised representations. Our investigation challenges the validity of this assumption. Using theoretical frameworks for the analysis of neural networks, we show a strong dependence of specialisation on the initial condition. More precisely, we show that weight imbalance and high weight entropy can favour specialised solutions. We then apply these insights in the context of continual learning, first showing the emergence of a monotonic relation between task-similarity and forgetting in non-specialised networks. Finally, we show that specialization by weight imbalance is beneficial on the commonly employed elastic weight consolidation regularisation technique. Copyright © 2025, The Authors. All rights reserved.

关键词： Neural networks

AN EXPLaiNABLE ATTENTION MODEL FOR CERVICAL PRECANCER RISK CLASSIFICATION USING COLPOSCOPIC IMAGES

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Khare, Smith K. Booth, Berit Bargum Blanes-Vidal, Victoria Petersen, Lone Kjeld Nadimi, Esmaeil S. Applied AI and Data Science Unit Mærsk Mc-Kinney Møller Institute Faculty of Engineering University of Southern Denmark Odense Denmark Centre for Clinical Artificial Intelligence Odense University Hospital Odense Denmark Centre for Department of Gynecology and Obstetrics Odense University Hospital Odense Denmark Odense University Hospital Odense Denmark

Cervical cancer remains a major worldwide health issue, with early identification and risk assessment playing critical roles in effective preventive interventions. This paper presents the Cervix-aiD-Net model for cervical precancer risk classification. The study designs and evaluates the proposed Cervix-aiD-Net model based on patients colposcopy images. The model comprises a Convolutional Block Attention Module (CBAM) and convolutional layers that extract interpretable and representative features of colposcopic images to distinguish high-risk and low-risk cervical precancer. In addition, the proposed Cervix-aiD-Net model integrates four explainable techniques, namely gradient class activation maps, Local Interpretable Model-agnostic Explanations, CartoonX, and pixel rate distortion explanation based on output feature maps and input features. The evaluation using holdout and tenfold cross-validation techniques yielded a classification accuracy of 99.33% and 99.81%. The analysis revealed that CartoonX provides meticulous explanations for the decision of the Cervix-aiD-Net model due to its ability to provide the relevant piece-wise smooth part of the image. The effect of Gaussian noise and blur on the input shows that the performance remains unchanged up to Gaussian noise of 3% and blur of 10%, while the performance reduces thereafter. A comparison study of the proposed model’s performance compared to other deep learning approaches highlights the Cervix-aiD-Net model’s potential as a supplemental tool for increasing the effectiveness of cervical precancer risk assessment. The proposed method, which incorporates the CBAM and explainable artificial integration, has the potential to influence cervical cancer prevention and early detection, improving patient outcomes and lowering the worldwide burden of this preventable disease. © 2024, CC BY.

关键词： Diseases

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale ai 41

学校读者我要写书评

暂无评论

Position: Bayesian Deep Learning is Needed in the Age of Lar...

41st International Conference on Machine Learning, ICML 2024

作者： Papamarkou, Theodore Skoularidou, Maria Palla, Konstantina aitchison, Laurence Arbel, Julyan Dunson, David Filippone, Maurizio Fortuin, Vincent Hennig, Philipp Hernández-Lobato, José Miguel Hubin, Aliaksandr Immer, Alexander Karaletsos, Theofanis Khan, Mohammad Emtiyaz Kristiadi, Agustinus Li, Yingzhen Mandt, Stephan Nemeth, Christopher Osborne, Michael A. Rudner, Tim G.J. Rügamer, David Teh, Yee Whye Welling, Max Wilson, Andrew Gordon Zhang, Ruqi Department of Mathematics The University of Manchester Manchester United Kingdom Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge United States Spotify London United Kingdom Computational Neuroscience Unit University of Bristol Bristol United Kingdom Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University United States Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany Department of Computer Science Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge United Kingdom Department of Mathematics University of Oslo Oslo Norway Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative CA United States Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London United Kingdom Department of Computer Science UC Irvine Irvine United States Department of Mathematics and Statistics Lancaster University Lancaster United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Center for Data Science New York University New York United States Department of Statistics LMU Munich Munich Germany DeepMind London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences Center for Data Science Computer Science Department New York University New York United States Department of Computer Science Purdue University West Lafayette United States

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential. Copyright 2024 by the author(s)

关键词： Contrastive Learning

Iteration Complexity of Variational Quantum Algorithms

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kungurtsev, Vyacheslav Korpas, Georgios Marecek, Jakub Zhu, Elton Yechao Department of Computer Science Czech Technical University in Prague Karlovo nam. 13 Prague 2 Czech Republic Archimedes Research Unit on AI Data Science and Algorithms Athena Research and Innovation Center Marousi15125 Greece Fidelity Center for Applied Technology FMR LLC BostonMA02210 United States

There has been much recent interest in near-term applications of quantum computers, i.e., using quantum circuits that have short decoherence times due to hardware limitations. Variational quantum algorithms (VQA), wherein an optimization algorithm implemented on a classical computer evaluates a parametrized quantum circuit as an objective function, are a leading framework in this space. An enormous breadth of algorithms in this framework have been proposed for solving a range of problems in machine learning, forecasting, applied physics, and combinatorial optimization, among others. In this paper, we analyze the iteration complexity of VQA, that is, the number of steps that VQA requires until its iterates satisfy a surrogate measure of optimality. We argue that although VQA procedures incorporate algorithms that can, in the idealized case, be modeled as classic procedures in the optimization literature, the particular nature of noise in near-term devices invalidates the claim of applicability of off-the-shelf analyses of these algorithms. Specifically, noise makes the evaluations of the objective function via quantum circuits biased. Commonly used optimization procedures, such as SPSA and the parameter shift rule, can thus be seen as derivative-free optimization algorithms with biased function evaluations, for which there are currently no iteration complexity guarantees in the literature. We derive the missing guarantees and find that the rate of convergence is unaffected. However, the level of bias contributes unfavorably to both the constant therein, and the asymptotic distance to stationarity, i.e., the more bias, the farther one is guaranteed, at best, to reach a stationary point of the VQA objective. © 2022, CC BY.

关键词： Quantum computers

Jacobian Kolmogorov-Arnold Networks for Cervical Cancer Cell Classification

学校读者我要写书评

暂无评论

SSRN

SSRN 2025年

作者： Khare, Smith K. Nadimi, Esmaeil S. Blanes-Vidal, Victoria Applied AI and Data Science Unit Mærsk Mc-Kinney Møller Institute Faculty of Engineering University of Southern Denmark Denmark Centre for Clinical Artificial Intelligence Odense University Hospital Denmark

Cervical cancer is a primary cause of death in women throughout the world, and early identification using cell classification is essential for increasing survival rates. Timely and accurate detection of cancer cells is critical for promoting personalized treatment and clinical diagnostics. This paper introduces Conv-Jacobian Kolmogorov–Arnold Network (ConvJKAN), a novel deep-learning architecture specifically designed for high-accuracy cervical cancer cell classification from cytological images. The Conv-JKAN uniquely integrates convolutional neural networks with the Jacobian Kolmogorov–Arnold network, enabling enhanced feature extraction while maintaining computational efficiency. The model employs just three convolutional layers and three JKAN layers to capture intricate spatial and contextual patterns across varying resolutions, ensuring superior recognition of subtle cytopathological changes. The novelty of ConvJKAN lies in its hierarchical decomposition approach, where JKAN dissects high-dimensional functions into low-dimensional components using Jacobian polynomial-based sensitivity analysis. This novel technique enhances both interpretability and gradient flow, addressing common challenges in deep-learning-based medical diagnostics. To validate its robustness, Conv-JKAN was rigorously tested on three public cytology datasets, achieving high classification performance: 100%, 99.75%, and 96.52% accuracy in binary classification, and 99.7%, 98.73%, and 96.35% in multiclass classification on the Mendeley LBC, SIPaKMeD, and Herlev datasets, respectively. Furthermore, we integrated explainable artificial intelligence (Xai) techniques within Conv-JKAN to provide transparent and interpretable insights into the model’s decision-making, which is crucial for real-world clinical adoption. © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

PR024/#890 Performance of an artificial intelligence model for evaluation of colposcopic images compared to digital colposcopy and colposcopists impression

学校读者我要写书评

暂无评论

International Journal of Gynecological Cancer 2024年 34卷 A51-A52页

作者： Lone Kjeld Petersen Berit Bargum Booth Smith Khare Victoria Blanes-Vidal Pinar Bor Esmaeil Nadimi Odense University Hospital Department of Gynecology and Obstetrics Odense Denmark University of Southern Denmark Applied Ai and Data Science Unit the Mærsk Mc-kinney Møller Institute Odense Denmark Aarhus University Department of Clinical Medicine Aarhus N Denmark

Position: Bayesian deep learning is needed in the age of large-scale ai 24

学校读者我要写书评

暂无评论

Position: Bayesian deep learning is needed in the age of lar...

Proceedings of the 41st International Conference on Machine Learning

作者： Theodore Papamarkou Maria Skoularidou Konstantina Palla Laurence aitchison Julyan Arbel David Dunson Maurizio Filippone Vincent Fortuin Philipp Hennig José Miguel Hernández-Lobato Aliaksandr Hubin Alexander Immer Theofanis Karaletsos Mohammad Emtiyaz Khan Agustinus Kristiadi Yingzhen Li Stephan Mandt Christopher Nemeth Michael A. Osborne Tim G. J. Rudner David Rügamer Yee Whye Teh Max Welling Andrew Gordon Wilson Ruqi Zhang Department of Mathematics The University of Manchester Manchester UK Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge Spotify London UK Computational Neuroscience Unit University of Bristol Bristol UK Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany and Department of Computer Science Technical University of Munich Munich Germany and Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge UK Department of Mathematics University of Oslo Oslo Norway and Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative California Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London UK Department of Computer Science UC Irvine Irvine Department of Mathematics and Statistics Lancaster University Lancaster UK Department of Engineering Science University of Oxford Oxford UK Center for Data Science New York University New York Munich Center for Machine Learning Munich Germany and Department of Statistics LMU Munich Munich Germany DeepMind London UK and Department of Statistics University of Oxford Oxford UK Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences and Center for Data Science Computer Science Department New York University New York Department of Computer Science Purdue University West Lafayette

关键词：

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale ai

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Papamarkou, Theodore Skoularidou, Maria Palla, Konstantina aitchison, Laurence Arbel, Julyan Dunson, David Filippone, Maurizio Fortuin, Vincent Hennig, Philipp Hernández-Lobato, José Miguel Hubin, Aliaksandr Immer, Alexander Karaletsos, Theofanis Khan, Mohammad Emtiyaz Kristiadi, Agustinus Li, Yingzhen Mandt, Stephan Nemeth, Christopher Osborne, Michael A. Rudner, Tim G.J. Rügamer, David Teh, Yee Whye Welling, Max Wilson, Andrew Gordon Zhang, Ruqi Department of Mathematics The University of Manchester Manchester United Kingdom Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge United States Spotify London United Kingdom Computational Neuroscience Unit University of Bristol Bristol United Kingdom Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University United States Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany Department of Computer Science Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge United Kingdom Department of Mathematics University of Oslo Oslo Norway Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative CA United States Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London United Kingdom Department of Computer Science UC Irvine Irvine United States Department of Mathematics and Statistics Lancaster University Lancaster United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Center for Data Science New York University New York United States Department of Statistics LMU Munich Munich Germany DeepMind London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences Center for Data Science Computer Science Department New York University New York United States Department of Computer Science Purdue University West Lafayette United States

关键词： Large datasets

Governing ai-Driven Health Research: Are IRBs Up to the Task?

学校读者我要写书评

暂无评论

Ethics & human research 2021年第2期43卷 35-42页

作者： Friesen, Phoebe Douglas-Jones, Rachel Marks, Mason Pierce, Robin Fletcher, Katherine Mishra, Abhishek Lorimer, Jessica Véliz, Carissa Hallowell, Nina Graham, Mackenzie Chan, Mei Sum Davies, Huw Sallamuddin, Taj Assistant professor in the Biomedical Ethics Unit and the Department of Social Studies of Medicine at McGill University Associate professor of anthropological approaches to data and infrastructure head of the Technologies in Practice research group the codirector of the ETHOS Lab at the IT University of Copenhagen Assistant professor of law at Gonzaga University and the Edmond J. Safra/Petrie-Flom Centers Joint Fellow-in-Residence at Harvard University Technology and Society at the Tilburg Law School at Tilburg University Coordinator of Cyber Security Oxford and the founding administrator of the Computer Science Department Research Ethics Committee in the Department of Computer Science at the University of Oxford DPhil candidate at the Uehiro Centre for Practical Ethics at the University of Oxford DPhil candidate on the NEUROSEC team in the Department of Psychiatry at the University of Oxford Associate professor in the Faculty of Philosophy at the Institute for Ethics in AI as well as a tutorial fellow at Hertford College at the University of Oxford Codirector of the EPSRC Centre for Doctoral Training in Health Data Science and a professor at the Ethox Centre and Wellcome Centre for Ethics and Humanities at the University of Oxford Senior research fellow in data ethics at the Wellcome Centre for Ethics and Humanities in the Nuffield Department of Population Health at the University of Oxford DPhil student in the Nuffield Department of Population Health at the University of Oxford and a research fellow in the Department of Applied Health Research at University College London Lecturer in education at the School of Education and Sport at the University of Edinburgh Data protection and information lawyer

Many are calling for concrete mechanisms of oversight for health research involving artificial intelligence (ai). In response, institutional review boards (IRBs) are being turned to as a familiar model of governance. Here, we examine the IRB model as a form of ethics oversight for health research that uses ai. We consider the model's origins, analyze the challenges IRBs are facing in the contexts of both industry and academia, and offer concrete recommendations for how these committees might be adapted in order to provide an effective mechanism of oversight for health-related ai research. © 2021 by The Hastings Center. All rights reserved.

关键词： ai research oversight artificial intelligence ethics committees health-related ai research institutional review boards research ethics