检索结果-内蒙古大学图书馆

Disentangling Rotational Dynamics and Ordering Transitions in a System of Self-Organizing Protein Nanorods via Rotationally Invariant Latent Representations

引用

ACS NANO 2021年第4期15卷 6471-6480页

作者： Kalinin, Sergei, V Zhang, Shuai Valleti, Mani Pyles, Harley Baker, David De Yoreo, James J. Ziatdinov, Maxim Univ Washington Mat Sci & Engn Seattle WA 98195 USA Pacific Northwest Natl Lab Phys Sci Div Richland WA 99354 USA Univ Tennessee Bredesen Ctr Interdisciplinary Res Knoxville TN 37996 USA Univ Washington Dept Biochem Seattle WA 98195 USA Univ Washington Inst Prot Design Seattle WA 98195 USA Univ Washington Inst Prot Design Dept Biochem Seattle WA 98195 USA Univ Washington Howard Hughes Med Inst Seattle WA 98195 USA Oak Ridge Natl Lab Ctr Nanophase Mat Sci Oak Ridge TN 37831 USA Oak Ridge Natl Lab Computat Sci & Engn Div Oak Ridge TN 37831 USA

The dynamics of complex ordering systems with active rotational degrees of freedom exemplified by protein self-assembly is explored using a machine learning workflow that combines deep learning-based semantic segmentation and rotationally invariant variational autoencoder-based analysis of orientation and shape evolution. The latter allows for disentanglement of the particle orientation from other degrees of freedom and compensates for lateral shifts. The disentangled representations in the latent space encode the rich spectrum of local transitions that can now be visualized and explored via continuous variables. The time dependence of ensemble averages allows insight into the time dynamics of the system and, in particular, illustrates the presence of the potential ordering transition. Finally, analysis of the latent variables along the single-particle trajectory allows tracing these parameters on a single-particle level. The proposed approach is expected to be universally applicable for the description of the imaging data in optical, scanning probe, and electron microscopy seeking to understand the dynamics of complex systems where rotations are a significant part of the process.

关键词： self-assembly latent space models deep learning variational autoencoder representation learning

来源：评论

学校读者我要写书评

暂无评论

Structural relational inference actor-critic for multi-agent reinforcement learning

引用

NEUROCOMPUTING 2021年 459卷 383-394页

作者： Zhang, Xianjie Liu, Yu Xu, Xiujuan Huang, Qiong Mao, Hangyu Carie, Anil Dalian Univ Technol Sch Software Key Lab Ubiquitous Network & Serv Software Liaoni Dalian 116620 Peoples R China Okinawa Inst Sci & Technol Grad Univ 1919-1 Tancha Onna Okinawa 9040495 Japan Huawei Noahs Ark Lab 3 Xinxi Rd Beijing 100085 Peoples R China VIT AP Sch Comp Sci Amaravathi 522237 India

Multi-agent reinforcement learning (MARL) is essential for a wide range of high-dimensional scenarios and complicated tasks with multiple agents. Many attempts have been made for agents with prior domain knowledge and predefined structure. However, the interaction relationship between agents in a multi-agent system (MAS) in general is usually unknown, and previous methods could not tackle dynamical activities in an ever-changing environment. Here we propose a multi-agent Actor-Critic algo-rithm called Structural Relational Inference Actor-Critic (SRI-AC), which is based on the framework of centralized training and decentralized execution. SRI-AC utilizes the latent codes in variational autoen-coder (VAE) to represent interactions between paired agents, and the reconstruction error is based on Graph Neural Network (GNN). With this framework, we test whether the reinforcement learning learners could form an interpretable structure while achieving better performance in both cooperative and com-petitive scenarios. The results indicate that SRI-AC could be applied to complex dynamic environments to find an interpretable structure while obtaining better performance compared to baseline algorithms. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Multi-agent systems Deep reinforcement learning variational autoencoder Actor-critic Graph neural network

来源：评论

学校读者我要写书评

暂无评论

Generating Responses With a Given Syntactic Pattern in Chinese Dialogues

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2021年 29卷 2888-2898页

作者： Zhou, Yi Zheng, Xiaoqing Huang, Xuanjing Fudan Univ Sch Comp Sci Shanghai 200433 Peoples R China

Recently, many efforts have been devoted to generating responses expressing a specific emotion or relating to a given topic in a controlled manner. However, limited attention has been given to generating responses with a specified syntactic pattern, which makes it possible to imitate someone's way of speaking in dialogue. To fulfill this goal, we propose two models to generate syntax-aware responses: a gross-constraint and a specific-constraint model. The former controls the syntactic patterns of generated responses at sentence-level, while the latter works at smaller language units, such as words or phrases, being capable of manipulating the syntactic structures of responses in a more subtle manner. The extensive experimental results on two different datasets show that both the two models not only can generate meaningful responses with a specific and coherent structure but also improve on the diversity of generated responses, with similar gains in readability, relevance, and diversity as measured by human judges.

关键词： Syntactics Process control Speech processing Computer architecture Chatbots Training Task analysis Controlled text generation stylized dialogue response generation syntactic patterns variational autoencoder deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Modeling and Synthesis of Breast Cancer Optical Property Signatures With Generative Models

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2021年第6期40卷 1687-1701页

作者： Pardo, Arturo Streeter, Samuel S. Maloney, Benjamin W. Gutierrez-Gutierrez, Jose A. McClatchy, David M. Wells, Wendy A. Paulsen, Keith D. Lopez-Higuera, Jose M. Pogue, Brian W. Conde, Olga M. Univ Cantabria Photon Engn Grp Santander 39006 Spain Inst Invest Sanitaria Valdecilla IDIVAL Santander 39011 Spain Dartmouth Coll Thayer Sch Engn Hanover NH 03755 USA Massachusetts Gen Hosp Radiat Drug Treatment Design Lab Boston MA 02114 USA Dartmouth Coll Geisel Sch Med Hanover NH 03755 USA Ctr Invest Biomed Red Bioingn Biomat & Nanomed CI Zaragoza 50018 Spain

Is it possible to find deterministic relationships between optical measurements and pathophysiology in an unsupervised manner and based on data alone? Optical property quantification is a rapidly growing biomedical imaging technique for characterizing biological tissues that shows promise in a range of clinical applications, such as intraoperative breast-conserving surgery margin assessment. However, translating tissue optical properties to clinical pathology information is still a cumbersome problem due to, amongst other things, inter- and intrapatient variability, calibration, and ultimately the nonlinear behavior of light in turbid media. These challenges limit the ability of standard statistical methods to generate a simple model of pathology, requiring more advanced algorithms. We present a data-driven, nonlinear model of breast cancer pathology for real-time margin assessment of resected samples using optical properties derived from spatial frequency domain imaging data. A series of deep neural network models are employed to obtain sets of latent embeddings that relate optical data signatures to the underlying tissue pathology in a tractable manner. These self-explanatory models can translate absorption and scattering properties measured from pathology, while also being able to synthesize new data. The method was tested on a total of 70 resected breast tissue samples containing 137 regions of interest, achieving rapid optical property modeling with errors only limited by current semi-empirical models, allowing for mass sample synthesis and providing a systematic understanding of dataset properties, paving the way for deep automated margin assessment algorithms using structured light imaging or, in principle, any other optical imaging technique seeking modeling. Code is available.

关键词： Optical imaging Nonlinear optics Biomedical optical imaging Imaging Adaptive optics Pathology Optical scattering Biomedical optical imaging breast cancer tissue optical properties modeling pathology deep learning dimensionality reduction variational autoencoder convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Passive Sonar Target Classification Using Deep Generative β-VAE

引用

IEEE SIGNAL PROCESSING LETTERS 2021年 28卷 808-812页

作者： Chandran, Satheesh C. Kamal, Suraj Mujeeb, A. Supriya, M. H. Cochin Univ Sci & Technol Dept Elect Kochi 682022 India Cochin Univ Sci & Technol Int Sch Photon Kochi 682022 India

The intrinsic complexity associated with passive sonar data makes the task of target recognition extremely challenging. The conventional classifier architectures based on hand-engineered feature transforms often fail miserably to disentangle the high-dimensional non-linear structures in the observed target records. Although the modern deep learning algorithms through hierarchical feature learning yield acceptable success rates, they often require tremendous amounts of data when trained in a supervised manner. An unsupervised generative framework utilizing a variational autoencoder (VAE) is proposed in this work in order to create better disentangled representations for the downstream classification task. The disentanglement is further enforced using a hyperparameter beta. For the purpose of better segregating the spectro-temporal features, an intermediate non-linearly scaled time-frequency representation is also employed in conjunction with beta-VAE. Experimental analysis of various classifier configurations yields encouraging results in terms of data efficiency and classification accuracy on target records collected from various locations of the Indian Ocean.

关键词： Task analysis Target recognition Acoustics Signal processing algorithms Oceans Machine learning algorithms Decoding Passive sonar target recognition deep learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

CVAD - An unsupervised image anomaly detector

引用

SOFTWARE IMPACTS 2022年 11卷

作者： Guo, Xiaoyuan Gichoya, Judy Wawira Purkayastha, Saptarshi Banerjee, Imon Emory Univ Dept Comp Sci Atlanta GA 30322 USA Emory Univ Dept Radiol & Imaging Sci Atlanta GA 30322 USA Indiana Univ Purdue Univ Sch Informat & Comp Indianapolis IN 46202 USA Arizona State Univ Sch Comp Informat & Decis Syst Engn Tempe AZ 85287 USA

Detecting out-of-distribution samples for image applications plays an important role in safeguarding the reliability of machine learning model deployment. In this article, we developed a software tool to support our OOD detector CVAD -a self-supervised Cascade variational autoencoder-based Anomaly Detector , which can be easily applied to various image applications without any assumptions. The corresponding open-source software is published for better public research and tool usage.

关键词： Anomaly detection OOD detection variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Highly Productive 3D Printing Process to Transcend Intractability in Materials and Geometries via Interactive Machine-Learning-Based Technique

ADVANCED INTELLIGENT SYSTEMS

引用

ADVANCED INTELLIGENT SYSTEMS 2023年第7期5卷

作者： Kim, Yuseok Park, Suk Hee Pusan Natl Univ Sch Mech Engn Busan 46241 South Korea

Herein, a highly productive and defect-free 3D-printing system enforced by deep-learning (DL)-based anomaly detection and reinforcement-learning (RL)-based optimization processes is developed. Unpredictable defect factors, such as machine setting errors or unexpected material flow, are analyzed by image-based anomaly detection implemented using a variational autoencoder DL model. Real-time detection and in situ correction of defects are implemented by an autocalibration algorithm in conjunction with the DL system. In view of productivity enhancement, the optimized set of diversified printing speeds can be generated from virtual simulation of RL, which is established using a physics-based engineering model. The RL-simulated parameter set maximizes printing speed and minimizes deflection-related failures throughout the 3D-printing process. With the synergistic assistance of DL and RL techniques, the developed system can overcome the inherent challenging intractability of 3D printing in terms of material property and geometry, achieving high process productivity.

关键词： deep learning defect control reinforcement learning variational autoencoder 3D printing

来源：评论

学校读者我要写书评

暂无评论

Prediction of microstructure evolution at the atomic scale by deep generative model in combination with recurrent neural networks

引用

ACTA MATERIALIA 2023年第1期259卷

作者： Sase, Kohei Shibuta, Yasushi Univ Tokyo Dept Mat Engn 7-3-1 HongoBunkyo Ku Tokyo 1138656 Japan

A novel method to predict multi-atom cooperative phenomena at atomic scale is proposed based on a deep generative model in combination with recurrent neural network. The variational autoencoder (VAE) model successfully identifies three different crystal orientations in the polycrystalline nickel by using 10-dimensional latent variables and restores the image of atomic configurations reflecting the crystal orientation of each grain. Moreover, microstructure evolution of the polycrystalline iron is successfully predicted through three steps: dimensionality reduction of atomic coordinates from the MD simulation using the encoder, time evolution of latent variables using the long short-term memory (LSTM) model, and data restoration using the decoder. We successfully predict the microstructure that cannot be reproduced on the time scale of MD simulations by decoding latent variables in the future time from the LSTM model. This is a new attempt of acceleration of the MD simulation that differs significantly from conventional acceleration methods.

关键词： Molecular dynamics Microstructure Deep generative model Recurrent neural networks variational autoencoder Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Synthesis of Synthetic Hyperspectral Images with Controllable Spectral Variability Using a Generative Adversarial Network

引用

REMOTE SENSING 2023年第16期15卷 3919-3919页

作者： Palsson, Burkni Ulfarsson, Magnus O. Sveinsson, Johannes R. Univ Iceland Fac Elect & Comp Engn IS-105 Reykjavik Iceland

In hyperspectral unmixing (HU), spectral variability in hyperspectral images (HSIs) is a major challenge which has received a lot of attention over the last few years. Here, we propose a method utilizing a generative adversarial network (GAN) for creating synthetic HSIs having a controllable degree of realistic spectral variability from existing HSIs with established ground truth abundance maps. Such synthetic images can be a valuable tool when developing HU methods that can deal with spectral variability. We use a variational autoencoder (VAE) to investigate how the variability in the synthesized images differs from the original images and perform blind unmixing experiments on the generated images to illustrate the effect of increasing the variability.

关键词： hyperspectral unmixing synthetic hyperspectral images generative adversarial network variational autoencoder deep learning neural network

来源：评论

学校读者我要写书评

暂无评论

BioDSNN: a dual-stream neural network with hybrid biological knowledge integration for multi-gene perturbation response prediction

引用

BRIEFINGS IN BIOINFORMATICS 2024年第1期26卷 bbae617页

作者： Tan, Yuejun Xie, Linhai Yang, Hong Zhang, Qingyuan Luo, Jinyuan Zhang, Yanchun Guangzhou Univ Cyberspace Inst Adv Technol Guangzhou 510000 Peoples R China Zhejiang Normal Univ Sch Comp Sci & Technol Jinhua 321000 Peoples R China Natl Ctr Prot Sci Beijing State Key Lab Prote Beijing 100000 Peoples R China Int Acad Phronesis Med Guangzhou 510000 Peoples R China

Studying the outcomes of genetic perturbation based on single-cell RNA-seq data is crucial for understanding genetic regulation of cells. However, the high cost of cellular experiments and single-cell sequencing restrict us from measuring the full combination space of genetic perturbations and cell types. Consequently, a bunch of computational models have been proposed to predict unseen combinations based on existing data. Among them, generative models, e.g. variational autoencoder and diffusion models, have the superiority in capturing the perturbed data distribution, but lack a biologically understandable foundation for generalization. On the other side of the spectrum, Gene Regulation Networks or gene pathway knowledge have been exploited for more reasonable generalization enhancement. Unfortunately, they do not reach a balanced processing of the two data modalities, leading to a degraded fitting ability. Hence, we propose a dual-stream architecture. Before the information from two modalities are merged, the sequencing data are learned with a generative model while three types of knowledge data are comprehensively processed with graph networks and a masked transformer, enforcing a deep understanding of single-modality data, respectively. The benchmark results show an approximate 20% reduction in terms of mean squared error, proving the effectiveness of the model.

关键词： genetic perturbation predict biological knowledge masked attention variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：