英语习得与人为目的语环境的创造

"语言习得"与"语言学习"是外语教学理论研究中的两个重要概念,克拉申认为只有"习得"来的语言才能成为流利的口头表达,而"学习"只能起"监查"作用.在"学习"的条件下,通过营造人为目的语习得环境,以用为本,立足实践,学习者同样可以达到习得外语的目标.     

基于不确定性的飞行器分离可靠性建模与分析方法

为实现飞行器分离任务可靠性的定量分析和高效精确评估,研究了高超声速飞行器分离任务过程中各种不确定性因素对分离可靠性的影响,提出一种基于不确定性的飞行器分离可靠性建模与分析方法。面向高超声速飞行器分离任务需求,建立分离动力学仿真模型,综合考虑分离过程不确定性因素的影响,利用灵敏度分析方法识别主要不确定性因素,构建分离可靠性模型。针对此模型,提出一种改进主动学习Kriging(IAK)的分离可靠性分析方法,通过新的采样策略选取失效概率更大的采样点作为新增训练点,进行高效可靠性分析。实例结果表明,该方法能够准确描述不确定性因素对分离过程的影响,提升分离可靠性定量分析的精度和效率,为飞行器分离方案的精细化设计提供支撑。     

基于深度增强学习的卫星姿态控制方法

针对卫星在执行丢弃载荷或捕获目标等复杂任务时遭遇的姿态突然发生变化的问题,采用深度增强学习方法对卫星姿态进行控制,使卫星恢复稳定状态。具体来说,首先搭建飞行器的姿态动力学环境,并将连续的控制力矩输出离散化,然后采用Deep Q Network算法进行卫星自主姿态控制训练,以姿态角速度趋于稳定作为奖励获得离散行为的最优智能输出。仿真试验表明,面向空间卫星姿态控制的深度增强学习算法能够在卫星受到突发随机扰动后稳定卫星姿态,并能有效解决传统PD控制器依赖被控对象质量参数的难题。所提出的方法采用自主学习的方式对卫星姿态进行控制,具有很强的智能性和一定的普适性,在未来卫星执行复杂空间任务中的智能控制方面有着很好的应用潜力。     

基于优化字典学习算法的压缩数据收集

为了提高压缩数据收集对多样化传感数据的适应能力,同时抑制环境噪声对数据收集精度的影响,提出了一种优化字典学习算法来构造压缩数据收集中的稀疏字典。理论分析表明在压缩数据收集中由环境噪声导致的数据收集误差和稀疏字典的自相干程度正相关。为此在字典学习的过程中引入了自相干惩罚项来抑制环境噪声对数据收集精度的影响。该惩罚项还能减少字典学习过程中对训练数据的过拟合,从而进一步提高了该算法的稀疏表示能力。实验表明,该算法的稀疏表示能力高于同类字典学习算法,而且能有效地抑制环境噪声对压缩数据收集精度的影响。      

基于权值分配及多特征表示的在线多示例学习跟踪

针对复杂环境下目标跟踪过程中由于遮挡、目标姿势及光照条件变化引起跟踪漂移的问题,提出一种基于多示例学习（MIL）框架的在线视觉目标跟踪算法。该算法针对多示例跟踪算法采用单一haar-like特征不能准确描述目标外观变化及在学习过程中对样本包中各正负样本示例采用相同权值,忽略不同正负样本示例在学习过程中对包的重要性不同的特点,采用多特征联合表示目标外观构造分类器,通过将多特征互补特性融入在线多示例学习过程中,利用多特征的互补属性建立准确的目标外观模型,克服在线多示例跟踪算法对目标外观变化描述不足的问题;同时,依据不同正负样本示例对样本包的重要程度进行权值分配,提高跟踪精度。实验结果表明,本文跟踪算法对场景光线剧烈变化、遮挡、尺度变化及平面旋转等干扰具有较强的跟踪鲁棒性,通过对不同视频序列进行测试,文中算法在5组测试视频序列上的平均中心位置误差远小于对比增量式学习跟踪,仅为10.14像素,其对比算法IVT、MIL和OAB的中心位置误差分别为17.99、20.29和33.64像素。      

机器人运动的学习控制

机器人学习控制旨在采用简单的控制器结构和易于实现的控制算法,提高机器人轨迹动态跟踪精度。本文讨论了机器人控制研究中存在的困难,简要回顾了早期学习控制思想的形成和发展,重点介绍了近年来国内外有关机器人学习控制研究的现状。     

Rotating machinery fault detection and diagnosis based on deep domain adaptation: A survey

In practical mechanical fault detection and diagnosis, it is difficult and expensive to collect enough large-scale supervised data to train deep networks. Transfer learning can reuse the knowledge obtained from the source task to improve the performance of the target task, which performs well on small data and reduces the demand for high computation power. However, the detection performance is significantly reduced by the direct transfer due to the domain difference. Domain adaptation (DA) can transfer the distribution information from the source domain to the target domain and solve a series of problems caused by the distribution difference of data. In this survey, we review various current DA strategies combined with deep learning (DL) and analyze the principles, advantages, and disadvantages of each method. We also summarize the application of DA combined with DL in the field of fault diagnosis. This paper provides a summary of the research results and proposes future work based on analysis of the key technologies.     

Interface Familiarity Restores Active Advantage in a Virtual Exploration and Reconstruction Task in Children

Abstract

Active exploration is reportedly better than passive observation of spatial displacements in real environments, for the acquisition of relational spatial information, especially by children. However, a previous study using a virtual environment (VE) showed that children in a passive observation condition performed better than actives when asked to reconstruct in reality the environment explored virtually. Active children were unpractised in using the input device, which may have detracted from any active advantage, since input device operation may be regarded as a concurrent task, increasing cognitive load and spatial working memory demands. To examine this possibility, 7–8-year-old children in the present study were given 5 minutes of training with the joystick input device. When compared with passive participants for spatial learning, active participants gave a better performance than passives, placing objects significantly more accurately. The importance of interface training when using VEs for assessment and training was discussed.     

Mining Spatial Associations with Limited Sensory Information

Abstract

Human navigation in an unknown environment requires an understanding of the spatial relationships of the terrain. For example, a soldier who is on a reconnaissance mission in a new city needs to “know” the spatial layout of the surroundings with high confidence. Oftentimes, this understanding must be acquired within a very short amount of time and with limited sensory inputs. The soldier would benefit from a digital avatar that draws inferences about the spatial layout of the city based on an initial set of observations and guides the soldier either in further exploring the environment or in making decisions based on these inferences. In this paper, we present and evaluate an inductive approach to learning spatial associations using sensory data that is available from the simulation environment of a computer game, Unreal Tournament. We study two kinds of spatial relationships between nodes on a level of a game map: nodes that are placed near each other to satisfy some spatial requirement and nodes that are placed near each other to satisfy the design preferences of a level architect. We show that we can infer both kinds of relationships using an association rule mining algorithm. Furthermore, we show how to use an ontology to distinguish between these relationships in order to discover different types of spatial arrangements on a specific map. We discuss how the inferred associations can be used to control an avatar that makes recommendations for navigating unexplored areas on a map. We conclude with some thoughts on the applicability of our methods to scenarios in the real world, beyond the simulation environment of a game, and on how the learned associations can be represented and queried by a simple question-answer type system.