检索结果-内蒙古大学图书馆

Hyperspectral Image Denoising via Self-Modulating Convolutional Neural Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Torun, Orhan Yuksel, Seniha Esen Erdem, Erkut Imamoglu, Nevrez Erdem, Aykut Hacettepe University Institute of Science Beytepe Ankara 06800 Turkey Hacettepe University Department of Electrical and Electronics Engineering Beytepe Ankara 06800 Turkey Hacettepe University Department of Computer Engineering Beytepe Ankara 06800 Turkey National Institute of Advanced Industrial Science and Technology Digital Architecture Research Center Tokyo135-0064 Japan Koç University Department of Computer Engineering Sarıyer Istanbul34450 Turkey Koç University Is Bank AI Center Sarıyer Istanbul34450 Turkey

Compared to natural images, hyperspectral images (HSIs) consist of a large number of bands, with each band capturing different spectral information from a certain wavelength, even some beyond the visible spectrum. These characteristics of HSIs make them highly effective for remote sensing applications. That said, the existing hyperspectral imaging devices introduce severe degradation in HSIs. Hence, hyperspectral image denoising has attracted lots of attention by the community lately. While recent deep HSI denoising methods have provided effective solutions, their performance under real-life complex noise remains suboptimal, as they lack adaptability to new data. To overcome these limitations, in our work, we introduce a self-modulating convolutional neural network which we refer to as SM-CNN, which utilizes correlated spectral and spatial information. At the core of the model lies a novel block, which we call spectral self-modulating residual block (SSMRB), that allows the network to transform the features in an adaptive manner based on the adjacent spectral data, enhancing the network’s ability to handle complex noise. In particular, the introduction of SSMRB transforms our denoising network into a dynamic network that adapts its predicted features while denoising every input HSI with respect to its spatio-spectral characteristics. Experimental analysis on both synthetic and real data shows that the proposed SM-CNN outperforms other state-of-the-art HSI denoising methods both quantitatively and qualitatively on public benchmark datasets. Our code will be available at https://***/orhan-t/SM-CNN. © 2023, CC BY-NC-ND.

关键词： Convolution

Deep Multi-kernel Clustering Network

学校读者我要写书评

暂无评论

Deep Multi-kernel Clustering Network

IEEE International Conference on data Mining (ICDM)

作者： Lina Ren Ruizhang Huang Shengwei Ma Yongbin Qin Yanping Chen Chuan Lin State Key Laboratory of Public Big Data Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry College of Computer Science and Technology Guizhou University Guiyang China Department of Information Engineering Guizhou Light Industry Technical College Guiyang China

In this paper, a deep multi-kernel clustering network, named DMKCN, is proposed to learn a high-quality and structurally separable kernel representation for the clustering task. Specifically, a multi-kernel learner is proposed to choose a suitable kernel function by learning a suitable combination of kernel functions automatically. A kernel-aid encoder module, consisting of a series of multi-kernel learners, is proposed to learn the structurally separable kernel representation. Besides, a dual self-supervised mechanism, consisting of a kernel self-supervised strategy and a representation self-supervised strategy, is designed to uniformly optimize the kernel representation learning and structural partition. The kernel self-supervised strategy is developed to supervise the multi-kernel learners with the consideration of an objective of clustering task, the representation self-supervised strategy is developed to guide the optimization of kernel representation learning by reconstructing the raw data. Extensive experiments on six real-world datasets demonstrate the outstanding performance of our proposed DMKCN.

关键词：

Cell2Sentence: Teaching Large Language Models the Language of Biology 41

学校读者我要写书评

暂无评论

Cell2Sentence: Teaching Large Language Models the Language o...

41st International Conference on Machine Learning, ICML 2024

作者： Levine, Daniel Rizvi, Syed Asad Lévy, Sacha Pallikkavaliyaveetil, Nazreen Zhang, David Chen, Xingyu Ghadermarzi, Sina Wu, Ruiming Zheng, Zihe Vrkic, Ivan Zhong, Anna Raskin, Daphne Han, Insu de Oliveira Fonseca, Antonio Henrique Caro, Josue Ortega Karbasi, Amin Dhodapkar, Rahul M. van Dijk, David Department of Computer Science Yale University New HavenCT United States School of Engineering Applied Science University of Pennsylvania PhiladelphiaPA United States School of Computer and Communication Sciences Swiss Federal Institute of Technology Lausanne Lausanne Switzerland Department of Neuroscience Yale School of Medicine New HavenCT United States Wu Tsai Institute Yale University New HavenCT United States Google United States Yale Institute for Foundations of Data Science New HavenCT United States Yale School of Engineering and Applied Science New HavenCT United States Roski Eye Institute University of Southern California Los AngelesCA United States Yale School of Medicine New HavenCT United States Cardiovascular Research Center Yale School of Medicine New HavenCT United States Interdepartmental Program in Computational Biology & Bioinformatics Yale University New HavenCT United States

We introduce Cell2Sentence (C2S), a novel method to directly adapt large language models to a biological context, specifically single-cell transcriptomics. By transforming gene expression data into"cell sentences," C2S bridges the gap between natural language processing and biology. We demonstrate cell sentences enable the finetuning of language models for diverse tasks in biology, including cell generation, complex cell-type annotation, and direct data-driven text generation. Our experiments reveal that GPT-2, when fine-tuned with C2S, can generate biologically valid cells based on cell type inputs, and accurately predict cell types from cell sentences. This illustrates that language models, through C2S finetuning, can acquire a significant understanding of single-cell biology while maintaining robust text generation capabilities. C2S offers a flexible, accessible framework to integrate natural language processing with transcriptomics, utilizing existing models and libraries for a wide range of biological applications. Copyright 2024 by the author(s)

关键词： Gene expression

XNet-Enhanced Deep BSDE Method and Numerical Analysis

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zheng, Xiaotao Xia, Zhihong Li, Xin Yue, Xingye Center for Financial Engineering Soochow University Jiangsu Suzhou215008 China School of Natural Science Great Bay University Guangdong Dongguan523808 China Department of Mathematics Northwestern University EvanstonIL60208 United States Department of Computer Science Northwestern University EvanstonIL60208 United States Mathematical Modelling and Data Analytics Center Oxford Suzhou Centre for Advanced Research Jiangsu Suzhou215123 China

Solving high-dimensional semilinear parabolic partial differential equations (PDEs) challenges traditional numerical methods due to the"curse of dimensionality." Deep learning, particularly through the Deep BSDE method, offers a promising alternative by leveraging neural networks’ capability to approximate high-dimensional functions. This paper introduces a novel network architecture, XNet, which significantly enhances the computational efficiency and accuracy of the Deep BSDE method. XNet demonstrates superior approximation capabilities with fewer parameters, addressing the trade-off between approximation and optimization errors found in existing methods. We detail the implementation of XNet within the Deep BSDE framework and present results that show marked improvements in solving high-dimensional PDEs, potentially setting a new standard for such computations. © 2025, CC BY.

关键词： Numerical methods

MassSpecGym: a benchmark for the discovery and identification of molecules 24

学校读者我要写书评

暂无评论

MassSpecGym: a benchmark for the discovery and identificatio...

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Roman Bushuiev Anton Bushuiev Niek F. de Jonge Adamo Young Fleming Kretschmer Raman Samusevich Janne Heirman Fei Wang Luke Zhang Kai Dührkop Marcus Ludwig Nils A. Haupt Apurva Kalia Corinna Brungs Robin Schmid Russell Greiner Bo Wang David S. Wishart Li-Ping Liu Juho Rousu Wout Bittremieux Hannes Rost Tytus D. Mak Soha Hassoun Florian Huber Justin J.J. van der Hooft Michael A. Stravs Sebastian Böcker Josef Sivic Tomáš Pluskal Institute of Organic Chemistry and Biochemistry of the Czech Academy of Sciences and Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Czech Institute of Informatics Robotics and Cybernetics Czech Technical University Bioinformatics Group Wageningen University & Research Department of Computer Science University of Toronto Chair for Bioinformatics Institute for Computer Science Friedrich Schiller University Jena Department of Computer Science University of Antwerp Department of computing science University of Alberta and Alberta Machine Intelligence Institute Department of Molecular Genetics University of Toronto Bright Giant GmbH Department of Computer Science Tufts University Institute of Organic Chemistry and Biochemistry of the Czech Academy of Sciences Department of computing science and Department of Biological Sciences University of Alberta Department of Computer Science Aalto University Mass Spectrometry Data Center National Institute of Standards and Technology Department of Computer Science and Department of Chemical and Biological Engineering Tufts University Centre for Digitalisation and Digitality University of Applied Sciences Düsseldorf Bioinformatics Group Wageningen University & Research and Department of Biochemistry University of Johannesburg Eawag: Swiss Federal Institute of Aquatic Science and Technology

ISBN: (纸本)9798331314385

The discovery and identification of molecules in biological and environmental samples is crucial for advancing biomedical and chemical sciences. Tandem mass spectrometry (MS/MS) is the leading technique for high-throughput elucidation of molecular structures. However, decoding a molecular structure from its mass spectrum is exceptionally challenging, even when performed by human experts. As a result, the vast majority of acquired MS/MS spectra remain uninterpreted, thereby limiting our understanding of the underlying (bio)chemical processes. Despite decades of progress in machine learning applications for predicting molecular structures from MS/MS spectra, the development of new methods is severely hindered by the lack of standard datasets and evaluation protocols. To address this problem, we propose MassSpecGym - the first comprehensive benchmark for the discovery and identification of molecules from MS/MS data. Our benchmark comprises the largest publicly available collection of high-quality labeled MS/MS spectra and defines three MS/MS annotation challenges: de novo molecular structure generation, molecule retrieval, and spectrum simulation. It includes new evaluation metrics and a generalization-demanding data split, therefore standardizing the MS/MS annotation tasks and rendering the problem accessible to the broad machine learning community. MassSpecGym is publicly available at https://***/pluskal-lab/MassSpecGym.

关键词：

Optimizing Ethanol Production in Escherichia Coli Using a Hybrid of Particle Swarm Optimization and Artificial Bee Colony 22

学校读者我要写书评

暂无评论

Optimizing Ethanol Production in Escherichia Coli Using a Hy...

Proceedings of the 6th International Conference on Advances in Artificial Intelligence

作者： Mohamad Faiz Dzulkalnine Mohd Saberi Mohamad Yee Wen Choon Muhammad Akmal Remli Hany Alashwal Artificial Intelligence and Bioinformatics Research Group Faculty of Computing Universiti Teknologi Malaysia Malaysia Health Data Science Lab Department of Genetics and Genomics College of Medical and Health Sciences United Arab Emirates University UAE and Big Data Analytics Center United Arab Emirates University UAE Institute for Artificial Intelligence and Big Data Universiti Malaysia Kelantan Malaysia and Department of Data Science Universiti Malaysia Kelantan Malaysia Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University UAE and Big Data Analytics Center United Arab Emirates University UAE

ISBN: (纸本)9781450396943

Metabolic engineering for biomass production using microorganisms’ cell has received considerable attention in recent years. This is due to the biomass products being extensively used in the field of food additives, supplements, pharmaceuticals, and polymer materials. In this paper, ethanol production in Escherichia coli (E. coli) is the desired product. Sugarcane and corn are often used to produce ethanol. However, one of the problems to produce adequate amounts of ethanol is that large areas are needed to plant sugarcane and corn. Furthermore, the amount of time for the process of dry milling and wet milling is high, which are 40 to 50 hours and 24 to 48 hours, respectively. The wet laboratory is also having limitation on the production of ethanol in microorganisms because the amount of the ethanol produced is not satisfying. Hence, a lot of metabolic engineering techniques is introduced to enhance the production of ethanol in E. coli, such as gene knockout strategy, but the production is yet to meet the demand. Therefore, this paper proposes a hybrid algorithm of Particle Swarm Optimization with the Artificial Bee Colony algorithm (PSOABC) to identify the optimal set of gene knockout strategy to improve the ethanol production in E. coli. A list of genes to knockout, production of the desired product, and growth rate are presented in this paper. PSOABC has shown better performance in terms of production, growth rate and accuracy.

关键词： Gene Knockouts Particle Swarm Optimization Artificial Bee Colony Ethanol Flux Balance Analysis

Product states optimize quantum p-spin models for large p

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Anschuetz, Eric R. Gamarnik, David Kiani, Bobak T. Institute for Quantum Information and Matter Caltech Walter Burke Institute for Theoretical Physics Caltech MIT Center for Theoretical Physics MIT United States Operations Research Center Statistics and Data Science Center Sloan School of Management MIT United States John A. Paulson School of Engineering and Applied Sciences Harvard Department of Electrical Engineering and Computer Science MIT United States

We consider the problem of estimating the maximal energy of quantum p-local spin glass random Hamiltonians, the quantum analogues of widely studied classical spin glass models. Denoting by E∗(p) the (appropriately normalized) maximal energy in the limit of a large number of qubits n, we show that E∗(p) approaches √2 log 6 as p increases. This value is interpreted as the maximal energy of a much simpler so-called Random Energy Model, widely studied in the setting of classical spin glasses. Our most notable and (arguably) surprising result proves the existence of near-maximal energy states which are product states, and thus not entangled. Specifically, we prove that with high probability as n → ∞, for any E ∗(p) there exists a product state with energy ≥ E at sufficiently large constant p. Even more surprisingly, this remains true even when restricting to tensor products of Pauli eigenstates. Our approximations go beyond what is known from monogamy-of-entanglement style arguments—the best of which, in this normalization, achieve approximation error growing with n. Our results not only challenge prevailing beliefs in physics that extremely low-temperature states of random local Hamiltonians should exhibit non-negligible entanglement, but they also imply that classical algorithms can be just as effective as quantum algorithms in optimizing Hamiltonians with large locality—though performing such optimization is still likely a hard problem. Our results are robust with respect to the choice of the randomness (disorder) and apply to the case of sparse random Hamiltonian using Lindeberg’s interpolation method. The proof of the main result is obtained by estimating the expected trace of the associated partition function, and then matching its asymptotics with the extremal energy of product states using the second moment method. Copyright © 2023, The Authors. All rights reserved.

关键词： Hamiltonians

Towards Certifying '∞ Robustness using Neural Networks with '∞-dist Neurons 38

学校读者我要写书评

暂无评论

Towards Certifying '∞ Robustness using Neural Networks with...

38th International Conference on Machine Learning, ICML 2021

作者： Zhang, Bohang Cai, Tianle Lu, Zhou He, Di Wang, Liwei Key Laboratory of Machine Perception MOE School of EECS Peking University China Department of Electrical and Computer Engineering Princeton University United States Zhongguancun Haihua Institute for Frontier Information Technology China Department of Computer Science Princeton University United States Microsoft Research Center for Data Science Peking University China

ISBN: (纸本)9781713845065

It is well-known that standard neural networks, even with a high classification accuracy, are vulnerable to small '∞-norm bounded adversarial perturbations. Although many attempts have been made, most previous works either can only provide empirical verification of the defense to a particular attack method, or can only develop a certified guarantee of the model robustness in limited scenarios. In this paper, we seek for a new approach to develop a theoretically principled neural network that inherently resists '∞ perturbations. In particular, we design a novel neuron that uses '∞-distance as its basic operation (which we call '∞-dist neuron), and show that any neural network constructed with '∞-dist neurons (called '∞-dist net) is naturally a 1-Lipschitz function with respect to '∞-norm. This directly provides a rigorous guarantee of the certified robustness based on the margin of prediction outputs. We then prove that such networks have enough expressive power to approximate any 1-Lipschitz function with robust generalization guarantee. We further provide a holistic training strategy that can greatly alleviate optimization difficulties. Experimental results show that using '∞-dist nets as basic building blocks, we consistently achieve state-of-the-art performance on commonly used datasets: 93.09% certified accuracy on MNIST (∊ = 0.3), 35.42% on CIFAR-10 (∊ = 8/255) and 16.31% on TinyImageNet (∊ = 1/255). Copyright © 2021 by the author(s)

关键词： Neurons

The 2022 Far-field Speaker Verification Challenge: Exploring domain mismatch and semi-supervised learning under the far-field scenario

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Qin, Xiaoyi Li, Ming Bu, Hui Narayanan, Shrikanth Li, Haizhou Data Science Research Center Duke Kunshan University Kunshan China Department of Electrical & Computer Engineering National University of Singapore Singapore Signal Analysis and Interpretation Lab University of Southern California Los Angeles United States AI Shell Foundation Beijing China

FFSVC2022 is the second challenge of far-field speaker verification. To further explore the far-field scenario, FFSVC2022 provides the fully-supervised far-field speaker verification and proposes the semi-supervised far-field speaker verification. In contrast to FFSVC2020, FFSVC2022 focus on the single-channel scenario. In addition, a supplementary set for the FFSVC2020 dataset is released this year. The supplementary set consists of more recording devices and has the same data distribution as the FFSVC2022 evaluation set. This paper summarizes the FFSVC 2022, including tasks description, trial designing details, a baseline system and a summary of challenge results. The challenge results indicate substantial progress made in the field but also present that there are still difficulties with the far-field scenario. Copyright © 2022, The Authors. All rights reserved.

关键词： Speech recognition