Multilevel-in-width training for deep neural network regression

A common challenge in regression is that for many problems, the degrees of freedom required for a high-quality solution also allows for overfitting. Regularization is a class of strategies that seek to restrict the range of possible solutions so as to discourage overfitting while still enabling good solutions, and different regularization strategies impose different types of restrictions. In this paper, we present a multilevel regularization strategy that constructs and trains a hierarchy of neural networks, each of which has layers that are wider versions of the previous network's layers. We draw intuition and techniques from the field of Algebraic Multigrid (AMG), traditionally used for solving linear and nonlinear systems of equations, and specifically adapt the Full Approximation Scheme (FAS) for nonlinear systems of equations to the problem of deep learning. Training through V-cycles then encourage the neural networks to build a hierarchical understanding of the problem. We refer to this approach as multilevel-in-width to distinguish from prior multilevel works which hierarchically alter the depth of neural networks. The resulting approach is a highly flexible framework that can be applied to a variety of layer types, which we demonstrate with both fully connected and convolutional layers. We experimentally show with PDE regression problems that our multilevel training approach is an effective regularizer, improving the generalize performance of the neural networks studied.     

影响高浓度氧化石墨烯分散液流变行为的重要因素及群体平衡动力学分析

氧化石墨烯(GO)片的基面和边缘上存在大量的含氧官能团,能很好地分散在水中,因而具有很好的加工性和广阔的应用前景。在较高浓度范围下,GO水分散液中存在着强烈的竞争性相互作用,从而对流变行为产生较大影响。在本文中,通过稳态、动态等流变实验以及理论分析,研究了pH值、温度和不同的有机溶剂对GO分散液流变行为的影响。结果表明,降低pH值、适当增加温度以及加入吡啶均可促进GO水分散液从粘弹性液体到凝胶态的转变。利用DLVO (Deryagin-Landau-Verwey-Overbeek)理论,探讨了GO片之间的范德华作用力以及双电层排斥作用的相互关系,及其对流变性能的影响。通过群体平衡模型(PBE)分析了GO分散液的屈服应力与体积分数的正相关关系。同时,通过蠕变和松弛实验发现,高浓度的GO分散液中结构变化及流变行为在很多方面与高聚物相似,利用Poyting-Thomson模型能较好地拟合其粘弹性行为。上述研究结果为深入研究复杂的GO分散体系提供理论支撑和实验依据。     

研究性与系统性相结合的有机合成实验教学实践

为了培养学生的创新能力和实践能力,使学生较全面地掌握有机合成实验理论知识和实验技能,开展了有机合成实验研究性和系统性结合的教学探索和实践。在课程建设和教学过程中,贯彻以学生为主体的教学改革思路与方法。从教学内容和模式、授课方式、考核方式等多个教学环节进行探索研究,科教融合,结合实际课堂教学,倡导启发式教学方法。研究型教学模式的实施有效地调动了学生自主研究性学习的积极性,有利于提高学生的综合实践能力,促进实验教学与科学研究的衔接。     

双轴速率位置台全数字化控制系统实现

讨论了一种适用于双轴测试转台的全数字化控制系统结构。该系统采用了多单片机并行实现的主从分布式控制方法，不仅大大简化了系统硬件设计，提高了可靠性；而且其控制器完全由软件来实现，易于实现模拟电路难以实现的复杂的控制规律；同时也为在不改变硬件的前提下进一步扩展系统功能，改善系统的动、静特性提供了基础。实验表明，文中提出的全数字化控制系统结构完全能满足双轴测试转台的控制需要。     

高精度转台控制系统研究

—本文针对精密转台控制系统在大偏差下的不稳定问题，对其控制系统进行了分析和设计，同时对其高分辨率的指令系统进行了设计，为提高转台的精度及其动态性能提供了新的途径。     

旋翼尾流与地面干扰时地面涡现象的研究

用Ｎ－Ｓ方程对近地飞行时旋翼尾流与地面干扰时产生的地面涡现象进行了数值计算旋翼对流场的作用由分布在特定区域内的动量源项模拟结果表明，旋翼尾流撞到地面后的卷起和轴向流动的拉伸作用是形成地面涡的原因；地面边界层形成的二次分离涡向地面涡内输入（与尾流所携带的涡量）相反的涡量，而使地面涡保持平衡；地面涡的存在和运动使旋翼附近流场大大改变     

岩石（煤）的碎胀与压实特性研究

本文通过自行设计的一套岩石（煤）的松散和压实试验方案及相应的实验设备，对兖州矿区岩（煤）样进行了较为系统的碎胀与压实特性研究，测定了岩石（煤）的碎胀系数、碎胀曲线、压实曲线和侧压曲线．     

电流变学研究进展

电流变学是近年来新兴的一门学科。本文从电流变学的发展概况，电流变流体，电流变效应的机理和电流变体的应用等４个方面对电流变学的概貌做了阐述，力求能准确地反映国际上电流变学的发展现状。     

一种改进的变结构控制器在转台中的应用

针对变结构控制的抖振问题,本提出了一种新的解决方案,采用多切换面的改进变结构控制,在保证了理想滑动模态的抗干扰能力强、鲁棒性好的优点的同时,很好的削弱了系统抖振。仿真结果表明,这种控制规律应用在转台上取得了良好的控制效果。     

Catalytic activity of chiral chelating N-heterocyclic carbene palladium complexes towards asymmetric allylic alkylation

Abstract

The catalytic activity of a series of chiral heteroaryl coordinated chelating N-heterocyclic carbene (NHC) palladium complexes towards asymmetric allylic alkylation (AAA) were presented here. The effects of different N-substituents, NHC backbones and chelate rings on the catalytic activity and the enantioselectivity of the alkylation of (E)-1,3-diarylallyl acetates with dialkyl malonate were investigated. The results showed that, under the optimized conditions, complexes 3a, 3b, and 3i carrying the pyridinyl-coordinated five-membered chelate ring showed high catalytic activity and chiral induction efficiency. The corresponding alkylated products were obtained in high yields with moderate ee. Furthermore, it was found that the substituents of (E)-1,3-diarylallyl acetates and the type of the nucleophile affect the results as well.