Task’s Choice: Pruning-Based Feature Sharing (PBFS) for Multi-Task Learning

In most of the existing multi-task learning (MTL) models, multiple tasks’ public information is learned by sharing parameters across hidden layers, such as hard sharing, soft sharing, and hierarchical sharing. One promising approach is to introduce model pruning into information learning, such as sparse sharing, which is regarded as being outstanding in knowledge transferring. However, the above method performs inefficiently in conflict tasks, with inadequate learning of tasks’ private information, or through suffering from negative transferring. In this paper, we propose a multi-task learning model (Pruning-Based Feature Sharing, PBFS) that merges a soft parameter sharing structure with model pruning and adds a prunable shared network among different task-specific subnets. In this way, each task can select parameters in a shared subnet, according to its requirements. Experiments are conducted on three benchmark public datasets and one synthetic dataset; the impact of the different subnets’ sparsity and tasks’ correlations to the model performance is analyzed. Results show that the proposed model’s information sharing strategy is helpful to transfer learning and superior to the several comparison models.     

Microwave-Assisted Solution Synthesis of Metastable Intergrowth of AgInS2 Polymorphs

The intergrowth of stable and metastable AgInS₂ polymorphs was synthesized using a microwave-assisted synthesis. The samples were synthesized in water and in a deep eutectic solvent (DES) consisting of choline chloride and thiourea. An increase in the metal precursor concentration improved the crystallinity of the synthesized samples and affected the particle size. AgInS₂ cannot be synthesized from crystalline binary Ag₂S or In₂S₃ via this route. The solution synthesis reported here results in the intergrowth of the thermodynamically stable polymorph (space group I4¯2d, chalcopyrite structure) and the high-temperature polymorph (space group Pna2₁, wurtzite-like structure) that is metastable at room temperature. A scanning transmission microscopy (STEM) study revealed the intergrowth of tetragonal and orthorhombic polymorphs in a single particle and unambiguously established that the long-thought hexagonal wurtzite polymorph has pseudo-hexagonal symmetry and is best described with the orthorhombic unit cell. The solution-synthesized AgInS₂ polymorphs intergrowth has slightly lower bandgap values in the range of 1.73 eV–1.91 eV compared to the previously reported values for tetragonal I4¯2d (1.86 eV) and orthorhombic Pna2₁ (1.98 eV) polymorphs.     

基于UNet深度学习算法的东海大型漂浮藻类遥感监测

基于语义分割神经网络UNet,利用GOCI(Geostationary Ocean Color Imager)卫星传感器数据,构建出能够有效提取大型漂浮藻类的深度学习模型,实现了对大型漂浮藻类信息端到端、像素到像素的分割识别.验证结果表明:所提出的深度学习模型对验证集中大型漂浮藻类的平均识别精度达到88.54％;通过与...     

A Quantitative Comparison between Shannon and Tsallis–Havrda–Charvat Entropies Applied to Cancer Outcome Prediction

In this paper, we propose to quantitatively compare loss functions based on parameterized Tsallis–Havrda–Charvat entropy and classical Shannon entropy for the training of a deep network in the case of small datasets which are usually encountered in medical applications. Shannon cross-entropy is widely used as a loss function for most neural networks applied to the segmentation, classification and detection of images. Shannon entropy is a particular case of Tsallis–Havrda–Charvat entropy. In this work, we compare these two entropies through a medical application for predicting recurrence in patients with head–neck and lung cancers after treatment. Based on both CT images and patient information, a multitask deep neural network is proposed to perform a recurrence prediction task using cross-entropy as a loss function and an image reconstruction task. Tsallis–Havrda–Charvat cross-entropy is a parameterized cross-entropy with the parameter α . Shannon entropy is a particular case of Tsallis–Havrda–Charvat entropy for α=1 . The influence of this parameter on the final prediction results is studied. In this paper, the experiments are conducted on two datasets including in total 580 patients, of whom 434 suffered from head–neck cancers and 146 from lung cancers. The results show that Tsallis–Havrda–Charvat entropy can achieve better performance in terms of prediction accuracy with some values of α .     

大锥角药型罩聚能装药侵彻混凝土实验研究

采用脉冲X光照相及威力效应实验,对两种大锥角药型罩装药结构侵彻体的形成及它们对混凝土的侵彻能力进行了研究,获得了两种大锥角药型罩装药结构形成侵彻体的形状、头尾速度及它们对混凝土靶的侵彻参量,对比了半无限厚混凝土靶板及多层有限厚薄靶板对侵彻威力的影响。结果表明,在小炸高条件下,两种大锥角药型罩装药结构能够形成较理想的爆炸成型杆式侵彻体,在混凝土靶中形成孔深与孔径兼顾的孔道。     

深部岩体圆形巷道围岩松动圈形成机理数值试验研究

采用损伤力学和统计理论的单元本构模型,探讨深部岩体巷道围岩破坏规律, 利用岩石破裂过程分析软件RFPA$^{\rm 2D}$, 对深部 岩体中的圆形巷道的变形及非线性渐进破坏特征、巷道周边关键部位的位移和应力变化进行 了分析,研究了圆形巷道围岩松动圈的形成机理. 研究表明：巷道开挖后,其周边形成应力 集中带,随着围岩压力的持续作用,巷道周边产生塑性变形区,并沿径向形成裂纹;随着裂 纹的不断扩展,巷道周边出现松动破裂区,即松动圈. 产生破裂区后,应力集中程度减弱, 应力高峰点向远处转移.     

约束及增韧对氧化铝陶瓷抗射流侵彻性能的影响

基于DOP实验方法开展了2种约束氧化铝陶瓷抗射流侵彻性能系列实验研究,分别获取了AD95陶瓷及10%氧化锆增韧陶瓷抗射流侵彻过程的侵彻深度-时间（P-t）曲线及他们在验证靶上的剩余穿深,并与45钢的抗侵彻数据进行了对比。结果表明:2种陶瓷抗射流侵彻的防护因数均大于1;约束陶瓷抗射流侵彻能力得到了较大提高;增韧陶瓷抗射流侵彻能力优于AD95陶瓷。基于实验结果分析了约束陶瓷抗射流侵彻的机理,提出约束边界反射产生的回爆对射流稳定性的干扰是约束陶瓷抗射流侵彻能力提高的主要原因。     

配筋结构对弹丸侵彻过程影响的研究

本文提出的弹丸侵彻钢筋混凝土的解析模型,既考虑了弹丸侵彻过程中受到的动阻力与静阻力,又考虑了弹丸与钢筋发生碰撞时钢筋对弹丸的直接阻力.该解析模型的计算结果能反映弹丸与钢筋结构的作用过程,与测试数据符合较好.用该模型计算了配筋尺寸、网眼尺寸、配筋结构对侵彻深度、侵彻过程弹丸过载特性的影响.计算结果表明网眼间距越小,弹丸峰值负加速度越大;配筋直径增大,弹丸与钢筋的作用力显著增大,弹丸过载显著增大.     

基于矢量跟踪的SINS/GPS深组合导航方法

为了满足高动态用户及强噪声干扰条件下的应用需求,提出了一种基于矢量跟踪的SINS/GPS深组合导航方案。深组合方案利用组合卡尔曼滤波器反馈回路取代了传统接收机中独立、并行的跟踪环路,能够同时完成所有可视卫星信号跟踪和组合导航信息处理的任务;利用相关器残差来更新导航参数状态,同时根据已有的导航参数和星历信息推测GPS伪码相位和多普勒频移等信号跟踪参数,用以控制接收机的本地伪码、载波数控振荡器（NCO）,使本地伪码相位和载波频率与输入信号保持一致。最后,通过仿真验证表明,基于矢量跟踪的深组合方法不仅在GPS信号发生短暂中断期间,能够保证组合系统的导航精度和可靠性,而且在载噪比较低的环境中能够维持较好的伪码相位和载波频率跟踪性能。     

??????????Χ????????????????о?

针对红透山深部断层下巷道围岩破坏诱发的涌水现象,以该矿水文地质条件 为基础,建立了岩体水力学模型,应用岩石破裂过程渗流-应力耦合分析系统 (RFPA$^{\rm 2D}$-Flow)模拟研究了深部断层下巷道围岩破坏过程：裂隙形成、扩展到突水通 道最终贯通形成涌水的全过程. 通过对损伤区分布、应力场和渗流场的演化规律进行分析, 揭示了巷道应力重新分布诱发损伤及渗流涌水规律,对涌水通道进行模拟定位,为红透山铜 矿深部巷道支护防渗设计提供了科学依据.