检索结果-内蒙古大学图书馆

PhotoRedshift-MML: a multimodal machine learning method for estimating photometric redshifts of quasars

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hong, Shuxin Zou, Zhiqiang Luo, A-Li Kong, Xiao Yang, Wenyu Chen, Yanli College of Computer Nanjing University of Posts and Telecommunications Nanjing210023 China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing210023 China CAS Key Laboratory of Optical Astronomy National Astronomical Observatories Beijing100101 China School of Astronomy and Space Science University of Chinese Academy of Sciences Beijing100049 China

We propose a Multimodal Machine Learning method for estimating the Photometric Redshifts of quasars (PhotoRedshift-MML for short), which has long been the subject of many investigations. Our method includes two main models, i.e. the feature transformation model by multimodal representation learning, and the photometric redshift estimation model by multimodal transfer learning. The prediction accuracy of the photometric redshift was significantly improved owing to the large amount of information offered by the generated spectral features learned from photometric data via the MML. A total of 415,930 quasars from Sloan Digital Sky Survey (SDSS) data Release 17, with redshifts between 1 and 5, were screened for our experiments. We used |Δz| = |(zphot− zspec)/(1 + zspec)| to evaluate the redshift prediction and demonstrated a 4.04% increase in accuracy. With the help of the generated spectral features, the proportion of data with |Δz| Copyright © 2022, The Authors. All rights reserved.

关键词： Surveys

A Novel Gradient Descent Least Squares (GDLS) Algorithm for Efficient SMV Gridless Line Spectrum Estimation with Applications in Tomographic SAR Imaging

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Shi, Ruizhe Zhang, Zhe Qiu, Xiaolan Ding, Chibiao School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100190 China Suzhou Aerospace Information Research Institute Suzhou Key Laboratory of Intelligent Aerospace Big Data Application Technology Jiangsu Suzhou215123 China CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System Beijing100190 China

This paper presents a novel efficient method for gridless line spectrum estimation problem with single snapshot, namely the gradient descent least squares (GDLS) method. Conventional single snapshot (a.k.a. single measure vector or SMV) line spectrum estimation methods either rely on smoothing techniques that sacrifice the array aperture, or adopt the sparsity constraint and utilize compressed sensing (CS) method by defining prior grids and resulting in the off-grid problem. Recently emerged atomic norm minimization (ANM) methods achieved gridless SMV line spectrum estimation, but its computational complexity is extremely high;thus it is practically infeasible in real applications with large problem scales. Our proposed GDLS method reformulates the line spectrum estimations problem into a least squares (LS) estimation problem and solves the corresponding objective function via gradient descent algorithm in an iterative fashion with efficiency. The convergence guarantee, computational complexity, as well as performance analysis are discussed in this paper. Numerical simulations and real data experiments show that the proposed GDLS algorithm outperforms the state-of-the-art methods e.g., CS and ANM, in terms of estimation performances. It can completely avoid the off-grid problem, and its computational complexity is significantly lower than ANM. Our method has been tested in tomographic SAR (TomoSAR) imaging applications via simulated and real experiment data. Results show great potential of the proposed method in terms of better cloud point performance and eliminating the gridding effect. Copyright © 2022, The Authors. All rights reserved.

关键词： Spectrum analysis

Chinese News Text Classification and Its Application Based on Combined-Convolutional Neural Network

学校读者我要写书评

暂无评论

Journal of Computers (Taiwan) 2022年第4期33卷 1-14页

作者： Liu, Kai-Feng Zhang, Yu Zhang, Quan-Xin Wang, Yan-Ge Gao, Kai-Long Jiangsu Vocational College of Finance and Economics Huaian223003 China School of Electrical and Information Engineering Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture Beijing100044 China State Key Laboratory in China for GeoMechanics and Deep Underground Engineering China University of Mining & Technology Beijing100083 China School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China

A method based on combined-convolutional neural network (Combined-CNN) for Chinese news text classification is proposed. First of all, in order to solve the problem of a lack of special term set for Chinese news classification, a vocabulary suitable for Chinese long text classification is made by constructing a data index method. The Word2Vec pre-trained model was used to embed the text features word vectors. Second, by optimizing the structure of the classical convolutional neural network (CNN) model, a new idea of Combined-CNN model is proposed, which solves the problem of incomplete feature extraction of local text blocks and improves the accuracy rate of Chinese news text classification. Effective model regularization and RAdam optimization algorithm are designed in the model to enhance the model training effect. The experimental results show that the precision of the Combined-CNN model for Chinese news text classification reaches 93.69%. Compared with traditional machine learning methods and deep learning algorithms, the accuracy rate is improved by a maximum of 11.82% and 1.9%, respectively, and it is better than the comparison model in Recall and F-Measure. Finally, the Chinese news classification algorithm of the Combined-CNN is applied to realize a personalized recommendation system. © 2022 Computer Society of the Republic of China. All rights reserved.

关键词： Recommender systems

AdAUC: End-to-end Adversarial AUC Optimization Against Long-tail Problems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hou, Wenzheng Xu, Qianqian Yang, Zhiyong Bao, Shilong He, Yuan Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Alibaba Group Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Artificial Intelligence Research Center Peng Cheng Laboratory Shenzhen China

It is well-known that deep learning models are vulnerable to adversarial examples. Existing studies of adversarial training have made great progress against this challenge. As a typical trait, they often assume that the class distribution is overall balanced. However, long-tail datasets are ubiquitous in a wide spectrum of applications, where the amount of head class instances is larger than the tail classes. Under such a scenario, AUC is a much more reasonable metric than accuracy since it is insensitive toward class distribution. Motivated by this, we present an early trial to explore adversarial training methods to optimize AUC. The main challenge lies in that the positive and negative examples are tightly coupled in the objective function. As a direct result, one cannot generate adversarial examples without a full scan of the dataset. To address this issue, based on a concavity regularization scheme, we reformulate the AUC optimization problem as a saddle point problem, where the objective becomes an instance-wise function. This leads to an end-to-end training protocol. Furthermore, we provide a convergence guarantee of the proposed algorithm. Our analysis differs from the existing studies since the algorithm is asked to generate adversarial examples by calculating the gradient of a min-max problem. Finally, the extensive experimental results show the performance and robustness of our algorithm in three long-tail datasets. © 2022, CC BY.

关键词： Deep learning

TomoSAR-ALISTA: Efficient TomoSAR imaging via deep unfolded network

学校读者我要写书评

暂无评论

TomoSAR-ALISTA: Efficient TomoSAR imaging via deep unfolded ...

International Conference on Radar Systems (RADAR 2022)

作者： M. Wang Z. Zhang Y. Wang S. Gao X. Qiu Key Laboratory of Technology in Geo-spatial Information Processing and Application System Chinese Academy of Sciences Beijing 100190 People's Republic of China Key Laboratory of Intelligent Aerospace Big Data Application Technology Suzhou 215123 People's Republic of China Electrical and Computer Engineering Department George Mason University Fairfax VA 22030 USA

ISBN: (数字)9781839537776

Synthetic aperture radar (SAR) tomography (TomoSAR) has attracted remarkable interest for its ability in achieving threedimensional reconstruction along the elevation direction from multiple observations. In recent years, compressed sensing (CS) technique has been introduced into TomoSAR considering for its super-resolution ability with limited samples. Whereas, the CS-based methods suffer from several drawbacks, including weak noise resistance, high computational complexity and complex parameter fine-tuning. Among the different CS algorithms, iterative soft-thresholding algorithm (ISTA) is widely used as a robust reconstruction approach, however, the parameters in the ISTA are manually chosen, which usually requires a time-consuming fine-tuning process to achieve the best performance. Aiming at efficient TomoSAR imaging, a novel sparse unfolding network named analytic learned ISTA (ALISTA) is proposed towards the TomoSAR imaging problem in this paper, and the key parameters of ISTA are learned from training data via deep learning to avoid complex parameter fine-tuning and significantly relieves the training burden. In addition, experiments verify that it is feasible to use traditional CS algorithms as training labels, which provides a tangible supervised training method to achieve better 3D reconstruction performance even in the absence of labeled data in real applications.

关键词：

IGNet: Constructing Rooted Phylogenetic Networks Based on Incompatible Graphs 15th

学校读者我要写书评

暂无评论

IGNet: Constructing Rooted Phylogenetic Networks Based on In...

15th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2019, co-located with the 5th International Conference on Harmony Search, Soft Computing and Applications, ICHSA 2019

作者： Wang, Juan Guo, Maozu School of Computer Science Inner Mongolia University Hohhot010021 China School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing100044 China Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing100044 China

ISBN: (纸本)9783030325909

Phylogenetic networks are used in biology to describe reticulate or non-treelike evolution events. Thus, constructing phylogenetic networks is essential for the research on the evolution of species. IGNet is a web-based server for on-line construction of rooted phylogenetic networks from rooted phylogenetic trees based on an incompatible graph. Two methods, and BIMLR, were introduced and implemented in IGNet to help users construct rooted phylogenetic networks rapidly and efficiently. Besides the on-line computation service, the IGNet also provides downloadable Java programs of and BIMLR for off-line construction of rooted phylogenetic networks. IGNet is availability from http://***. © 2020, Springer Nature Switzerland AG.

关键词： Biology

Interventional Multi-Instance Learning with Deconfounded Instance-Level Prediction

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lin, Tiancheng Xu, Hongteng Yang, Canqian Xu, Yi Shanghai Key Lab of Digital Media Processing and Transmission Shanghai Jiao Tong University China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China JD Explore Academy China

When applying multi-instance learning (MIL) to make predictions for bags of instances, the prediction accuracy of an instance often depends on not only the instance itself but also its context in the corresponding bag. From the viewpoint of causal inference, such bag contextual prior works as a confounder and may result in model robustness and interpretability issues. Focusing on this problem, we propose a novel interventional multi-instance learning (IMIL) framework to achieve deconfounded instance-level prediction. Unlike traditional likelihood-based strategies, we design an Expectation-Maximization (EM) algorithm based on causal intervention, providing a robust instance selection in the training phase and suppressing the bias caused by the bag contextual prior. Experiments on pathological image analysis demonstrate that our IMIL method substantially reduces false positives and outperforms state-of-the-art MIL methods. Copyright © 2022, The Authors. All rights reserved.

关键词： Forecasting

Online Attentive Kernel-Based Temporal Difference Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Yang, Guang Chen, Xingguo Yang, Shangdong Wang, Huihui Dong, Shaokang Gao, Yang The the Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications National Engineering Laboratory for Agri-Product Quality Traceability Beijing Technology and Business University China The State Key Laboratory for Novel Software Technology Nanjing University China The PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education Jiangsu Key Lab of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology China

With rising uncertainty in the real world, online Reinforcement Learning (RL) has been receiving increasing attention due to its fast learning capability and improving data efficiency. However, online RL often suffers from complex Value Function Approximation (VFA) and catastrophic interference, creating difficulty for the deep neural network to be applied to an online RL algorithm in a fully online setting. Therefore, a simpler and more adaptive approach is introduced to evaluate value function with the kernel-based model. Sparse representations are superior at handling interference, indicating that competitive sparse representations should be learnable, non-prior, non-truncated and explicit when compared with current sparse representation methods. Moreover, in learning sparse representations, attention mechanisms are utilized to represent the degree of sparsification, and a smooth attentive function is introduced into the kernel-based VFA. In this paper, we propose an Online Attentive Kernel-Based Temporal Difference (OAKTD) algorithm using two-timescale optimization and provide convergence analysis of our proposed algorithm. Experimental evaluations showed that OAKTD outperformed several Online Kernel-based Temporal Difference (OKTD) learning algorithms in addition to the Temporal Difference (TD) learning algorithm with Tile Coding on public Mountain Car, Acrobot, CartPole and Puddle World tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Learning algorithms

FABind: Fast and Accurate Protein-Ligand Binding

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pei, Qizhi Gao, Kaiyuan Wu, Lijun Zhu, Jinhua Xia, Yingce Xie, Shufang Qin, Tao He, Kun Liu, Tie-Yan Yan, Rui Gaoling School of Artificial Intelligence Renmin University of China China School of Computer Science and Technology Huazhong University of Science and Technology China Microsoft Research AI4Science China School of Information Science and Technology University of Science and Technology of China China Engineering Research Center of Next-Generation Intelligent Search and Recommendation Ministry of Education China Beijing Key Laboratory of Big Data Management and Analysis Methods China

Modeling the interaction between proteins and ligands and accurately predicting their binding structures is a critical yet challenging task in drug discovery. Recent advancements in deep learning have shown promise in addressing this challenge, with sampling-based and regression-based methods emerging as two prominent approaches. However, these methods have notable limitations. Sampling-based methods often suffer from low efficiency due to the need for generating multiple candidate structures for selection. On the other hand, regression-based methods offer fast predictions but may experience decreased accuracy. Additionally, the variation in protein sizes often requires external modules for selecting suitable binding pockets, further impacting efficiency. In this work, we propose FABind, an end-to-end model that combines pocket prediction and docking to achieve accurate and fast protein-ligand binding. FABind incorporates a unique ligand-informed pocket prediction module, which is also leveraged for docking pose estimation. The model further enhances the docking process by incrementally integrating the predicted pocket to optimize protein-ligand binding, reducing discrepancies between training and inference. Through extensive experiments on benchmark datasets, our proposed FABind demonstrates strong advantages in terms of effectiveness and efficiency compared to existing methods. Our code is available at Github3 Copyright © 2023, The Authors. All rights reserved.

关键词： Ligands