非高斯环境下的深度学习脉冲信号去噪与重构*

侧扫声呐进行沉底小目标探测时,底混响是主要背景干扰。底混响通常是一种非平稳、非高斯的带限噪声,它使得白噪声条件下的滤波器性能受到限制。在混响背景下常利用自回归模型对接收信号进预行白化处理,但对于实际侧扫声呐应用,白化后直接匹配滤波的处理效果不甚理想。针对此问题,在自回归模型预白化的基础上,提出采用一种次最佳检测与多分辨二分奇异值分解相结合的改进方法。该方法首先对接收信号进行分段处理,利用改进Burg算法估计每段数据自回归模型的系数及阶数;然后构造白化滤波器对分段数据预白化,并对白化后的数据进行多分辨二分奇异值分解;最后应用ostu方法对原始声图和处理后的声图进行目标检测。仿真与实验结果表明,该方法明显提高了信混比,改善了侧扫声呐沉底静态小目标的成图质量,有利于后期实现基于图像的目标自动检测。     

Deep Learning-Based Joint CSI Feedback and Hybrid Precoding in FDD mmWave Massive MIMO Systems

In this paper, we propose an end-to-end deep learning approach to realize channel state information (CSI) feedback and hybrid precoding for millimeter wave massive multiple-input multiple-output systems in the frequency division duplexing mode. Different from conventional approaches that treat the CSI reconstruction and hybrid precoding as separate components, we propose a new end-to-end learning method bypassing the channel reconstruction phase, and design the hybrid precoders and combiners directly from the feedback codewords (a compressed version of the CSI). More specifically, we design a neural network composed of the CSI feedback and hybrid precoding. Experiment results show that our proposed network can achieve better performance than conventional hybrid precoding schemes that reserve channel reconstruction, especially when the feedback resources are limited.     

Survey on Self-Supervised Learning: Auxiliary Pretext Tasks and Contrastive Learning Methods in Imaging

Although deep learning algorithms have achieved significant progress in a variety of domains, they require costly annotations on huge datasets. Self-supervised learning (SSL) using unlabeled data has emerged as an alternative, as it eliminates manual annotation. To do this, SSL constructs feature representations using pretext tasks that operate without manual annotation, which allows models trained in these tasks to extract useful latent representations that later improve downstream tasks such as object classification and detection. The early methods of SSL are based on auxiliary pretext tasks as a way to learn representations using pseudo-labels, or labels that were created automatically based on the dataset’s attributes. Furthermore, contrastive learning has also performed well in learning representations via SSL. To succeed, it pushes positive samples closer together, and negative ones further apart, in the latent space. This paper provides a comprehensive literature review of the top-performing SSL methods using auxiliary pretext and contrastive learning techniques. It details the motivation for this research, a general pipeline of SSL, the terminologies of the field, and provides an examination of pretext tasks and self-supervised methods. It also examines how self-supervised methods compare to supervised ones, and then discusses both further considerations and ongoing challenges faced by SSL.     

激光诱导击穿光谱对U元素的定量分析

铀矿是核领域最重要的矿产资源之一,快速、有效勘探铀矿资源能促进核领域平稳、健康发展。激光诱导击穿光谱(LIBS)技术具备多目标元素现场快速检测的优点,能实现铀矿资源准确、快速的现场分析。本工作基于LIBS技术对铀矿中U元素进行了定量分析,对比了偏最小二乘(PLS)和随机森林(RF)两种机器学习算法的定量效果。结果显示,RF模型的定量线性相关系数为0.996,对三个验证集的相对误差分别是22.33%、12.79%和12.04%;PLS模型的定量线性相关系数为0.997,对三个验证集的相对误差分别是4.33%、6.63%和6.85%。对比结果表明,本研究中的PLS模型定量准确度更高,同RF算法相比,PLS算法更适用于铀矿中U的LIBS定量分析。     

Robust Aggregation for Federated Learning by Minimum γ-Divergence Estimation

Federated learning is a framework for multiple devices or institutions, called local clients, to collaboratively train a global model without sharing their data. For federated learning with a central server, an aggregation algorithm integrates model information sent from local clients to update the parameters for a global model. Sample mean is the simplest and most commonly used aggregation method. However, it is not robust for data with outliers or under the Byzantine problem, where Byzantine clients send malicious messages to interfere with the learning process. Some robust aggregation methods were introduced in literature including marginal median, geometric median and trimmed-mean. In this article, we propose an alternative robust aggregation method, named γ-mean, which is the minimum divergence estimation based on a robust density power divergence. This γ-mean aggregation mitigates the influence of Byzantine clients by assigning fewer weights. This weighting scheme is data-driven and controlled by the γ value. Robustness from the viewpoint of the influence function is discussed and some numerical results are presented.     

A New Look at the Spin Glass Problem from a Deep Learning Perspective

Spin glass is the simplest disordered system that preserves the full range of complex collective behavior of interacting frustrating elements. In the paper, we propose a novel approach for calculating the values of thermodynamic averages of the frustrated spin glass model using custom deep neural networks. The spin glass system was considered as a specific weighted graph whose spatial distribution of the edges values determines the fundamental characteristics of the system. Special neural network architectures that mimic the structure of spin lattices have been proposed, which has increased the speed of learning and the accuracy of the predictions compared to the basic solution of fully connected neural networks. At the same time, the use of trained neural networks can reduce simulation time by orders of magnitude compared to other classical methods. The validity of the results is confirmed by comparison with numerical simulation with the replica-exchange Monte Carlo method.     

Effectiveness of Biologically Inspired Neural Network Models in Learning and Patterns Memorization

Purpose: In this work, we propose an implementation of the Bienenstock–Cooper–Munro (BCM) model, obtained by a combination of the classical framework and modern deep learning methodologies. The BCM model remains one of the most promising approaches to modeling the synaptic plasticity of neurons, but its application has remained mainly confined to neuroscience simulations and few applications in data science. Methods: To improve the convergence efficiency of the BCM model, we combine the original plasticity rule with the optimization tools of modern deep learning. By numerical simulation on standard benchmark datasets, we prove the efficiency of the BCM model in learning, memorization capacity, and feature extraction. Results: In all the numerical simulations, the visualization of neuronal synaptic weights confirms the memorization of human-interpretable subsets of patterns. We numerically prove that the selectivity obtained by BCM neurons is indicative of an internal feature extraction procedure, useful for patterns clustering and classification. The introduction of competitiveness between neurons in the same BCM network allows the network to modulate the memorization capacity of the model and the consequent model selectivity. Conclusions: The proposed improvements make the BCM model a suitable alternative to standard machine learning techniques for both feature selection and classification tasks.     

基于密集连接时延神经网络的说话人识别算法*

说话人识别技术是一项重要的生物特征识别技术。近年来,使用深度神经网络提取发声特征的说话人识别算法取得了突出成果。时延神经网络作为其中的典型代表之一已被证明具有出色的特征提取能力。为进一步提升识别准确率并节约计算资源,通过对现有的说话人识别算法进行研究,提出一种带有注意力机制的密集连接时延神经网络用于说话人识别。密集连接的网络结构在增强不同网络层之间的信息复用的同时能有效控制模型体积。通道注意力机制和帧注意力机制帮助网络聚焦于更关键的细节特征,使得通过统计池化提取出的说话人特征更具有代表性。实验结果表明,在VoxCeleb1测试数据集上取得了1.40%的等错误率（EER）和0.15的最小检测代价标准（DCF）,证明了在说话人识别任务上的有效性。     

求解大规模矛盾方程组的最小二乘支持向量机算法

房价预测、共享单车出租数量预测、空气污染情况预测等常涉及矛盾方程组求解,对其数值求解方法研究具有重要的理论意义与应用价值。当矛盾方程组规模过大时,用传统的最小二乘法求解,不仅计算量大,而且由于误差积累使最终结果的准确性不高。鉴于此,采用机器学习中的最小二乘支持向量机（least squares support vector machine,LS-SVM）算法求解大规模矛盾方程组,并分别针对线性、非线性、单变量、多变量矛盾方程组进行了数值求解。数值结果表明,数据类型和数据量的变化对结果的影响不大,因此只要选取适当的参数就可建立合适的模型,得到高精度的预测结果。     

基于深度学习的岩石薄片矿物自动识别方法

岩石薄片矿物识别是岩石学研究工作的基础,亦是进一步认识岩石种类、成因机理、物质运移和演化历史的基础。传统的矿物识别主要依靠光学显微镜进行人工鉴定,经济成本和时间成本较高、效率较低,且受制于专家个人经验与主观判断。随着深度学习技术的发展,计算机能从图像中自动提取更准确的语义信息,从而为岩石薄片图像的智能分析提供有效途径。提出了一种基于深度学习的岩石薄片矿物自动识别方法,利用深度卷积神经网络自动提取岩石薄片图像中不同矿物的有效特征,并对其进行语义分割与识别,综合利用单偏光与正交偏光2种光性图像实现了对矿物的自动识别。对南京大学岩石教学薄片显微图像数据集进行了矿物识别测试,结果表明,总体精度为86.7%,Kappa系数为0.818,识别结果较传统图像分类方法更准确。