一种量子神经网络模型及改进学习算法

提出一种量子BP网络模型及改进学习算法,该BP网络模型首先基于量子学中一位相移门和两位受控非门的通用性,构造出一种量子神经元,然后由该量子神经元构造隐含层,采用梯度下降法进行学习。输出层采用传统神经元构造,采用基于改进的带动量自适应学习率梯度下降法学习。在UCI两个数据集上采用该模型及算法,实验结果表明该方法比传统的BP网络具有较好的收敛速度和正确率。     

论协作型计算机网络教学与学生创造性学习的培养

目前在高等学校教学改革中,基于计算机网络环境下的教学已成趋势。以《大学计算机基础》教学为例,结合网络教学实践,旨在探讨如何利用网络自主学习的平台,培养学生的创造性学习能力。     

非圆曲线的数控处理及程序实现

引用优化设计中一维搜索和黄金分割法,针对数控加工中非圆曲线的处理,给出实用、简洁和新颖的宏程序实现方法,解决在数控系统中求解方程组的问题,是数控用户快速解决相关应用问题的有效手段。     

On the usability and likeability of virtual reality games for education: The case of VR-ENGAGE

Educational software games aim at increasing the students’ motivation and engagement while they learn. However, if software games are targeted to school classrooms they have to be usable and likeable by all students. Usability of virtual reality games may be a problem because these games tend to have complex user interfaces so that they are more attractive. Moreover, if the games acquire an educational content they may lose the attractiveness and appeal that they have on users who are familiar with commercial games. Consequently, likeability may also be questioned. In this paper, we address the issue of usability and likeability of a virtual reality game that is meant to teach students geography. We describe the evaluation experiments conducted, which involved three categories of students in terms of their level of game-playing expertise: novice, intermediate and expert game players. The evaluation results showed that the game was indeed usable and likeable but there was scope for usability and likeability improvement so that the educational benefits may be maximised for all categories of students. The evaluation studies reported in this paper, revealed important issues about further research on virtual reality educational games.     

Diffusional mobility for fcc phase of Al–Mg–Zn system and its applications

Diffusional mobility for fcc phase of the Al–Mg and Al–Mg–Zn systems was critically assessed by using the DICTRA software (Diffusion Controlled Transformation). Good agreement was obtained from comprehensive comparisons between the calculated and experimental diffusion coefficients. The developed mobility database enables reasonable prediction of diffusion and solidification behaviours resulting from interdiffusion, such as concentration profile of diffusion couples and solidification curve of the Al–Mg alloys.     

Learning to Locate Informative Features for Visual Identification

Object identification is a specialized type of recognition in which the category (e.g. cars) is known and the goal is to recognize an object’s exact identity (e.g. Bob’s BMW). Two special challenges characterize object identification. First, inter-object variation is often small (many cars look alike) and may be dwarfed by illumination or pose changes. Second, there may be many different instances of the category but few or just one positive “training” examples per object instance. Because variation among object instances may be small, a solution must locate possibly subtle object-specific salient features, like a door handle, while avoiding distracting ones such as specular highlights. With just one training example per object instance, however, standard modeling and feature selection techniques cannot be used. We describe an on-line algorithm that takes one image from a known category and builds an efficient “same” versus “different” classification cascade by predicting the most discriminative features for that object instance. Our method not only estimates the saliency and scoring function for each candidate feature, but also models the dependency between features, building an ordered sequence of discriminative features specific to the given image. Learned stopping thresholds make the identifier very efficient. To make this possible, category-specific characteristics are learned automatically in an off-line training procedure from labeled image pairs of the category. Our method, using the same algorithm for both cars and faces, outperforms a wide variety of other methods.     

Learning traversability models for autonomous mobile vehicles

Autonomous mobile robots need to adapt their behavior to the terrain over which they drive, and to predict the traversability of the terrain so that they can effectively plan their paths. Such robots usually make use of a set of sensors to investigate the terrain around them and build up an internal representation that enables them to navigate. This paper addresses the question of how to use sensor data to learn properties of the environment and use this knowledge to predict which regions of the environment are traversable. The approach makes use of sensed information from range sensors (stereo or ladar), color cameras, and the vehicle’s navigation sensors. Models of terrain regions are learned from subsets of pixels that are selected by projection into a local occupancy grid. The models include color and texture as well as traversability information obtained from an analysis of the range data associated with the pixels. The models are learned without supervision, deriving their properties from the geometry and the appearance of the scene. The models are used to classify color images and assign traversability costs to regions. The classification does not use the range or position information, but only color images. Traversability determined during the model-building phase is stored in the models. This enables classification of regions beyond the range of stereo or ladar using the information in the color images. The paper describes how the models are constructed and maintained, how they are used to classify image regions, and how the system adapts to changing environments. Examples are shown from the implementation of this algorithm in the DARPA Learning Applied to Ground Robots (LAGR) program, and an evaluation of the algorithm against human-provided ground truth is presented.

一种有腿机器人步态轨迹生成算法

目前存在一类有腿机器人,由于其底层动力学控制参数难于获取,行走设计无法使用已有的控制方法,现有的基于建模的步态存在缺乏完善规划,固定规划步态与实际步态相差较大的问题,针对这个问题,提出一种使用曲线拟合生成步态轨迹的想法,通过引入遗传算法,让机器人能自主的搜索良好的行走步态轨迹,在四足步行机器人平台上取得了良好的实验结果.     

基于VC＋＋的井架承载能力评估程序设计

针对井架承载能力评估过程中井架承载能力计算复杂、繁琐等问题,采用计算编程软件计算井架承栽能力有利于简化计算过程、提高评估效率与精度．在介绍井架承载能力评估计算方法的基础上,以VC＋＋为工具,编写了一套功能较为完善的计算评估程序。整套程序含四个功能模块,能按新、旧两种井架评定标准进行计算,经现场检验,效果良好。     

图像的平视化处理

摄像机拍摄图像时,会使物体在同一水平面上的边缘呈现曲线形状,给图像处理方法的实现和图像边缘位置的定位带来不便。这篇文章研究了把图像的曲线边缘变为直线边缘的图像平视化处理方法,推导了像素点和空间点的对应关系公式,陈述了图像平视化处理的思路,并对现场采集的图像进行了平视化处理。通过试验,这篇文章的平视化方法取得了较好的效果。