多模式对连接权矩阵的一种神经网络学习算法

该文提出多模式对连接权矩阵的一种神经网络学习算法,并给出了严格的理论证明。该算法能够将多个模糊模式对可靠地编码存储到尽可能少的连接权矩阵中,从而大大地减少存储空间,而且容易实现,并举例验证了它的有效性。     

Robot learning schemes that trade motion accuracy for command simplification

This study was inspired by the human motor control system in its ability to accommodate a wide variety of motions. By contrast, the biologically inspired robot learning controller usually encounters huge learning space problems in many practical applications. A hypothesis for the superiority of the human motor control system is that it may have simplified the motion command at the expense of motion accuracy. This tradeoff provides an insight into how fast and simple control can be achieved when a robot task does not demand high accuracy. Two motion command simplification schemes are proposed in this paper based on the equilibrium-point hypothesis for human motion control. Investigation into the tradeoff between motion accuracy and command simplification reported in this paper was conducted using robot manipulators to generate signatures. Signature generation involves fast handwriting, and handwriting is a human skill acquired via practice. Because humans learn how to sign their names after they learn how to write, in the second learning process, they somehow learn to trade motion accuracy for motion speed and command simplicity, since signatures are simplified forms of original handwriting. Experiments are reported that demonstrate the effectiveness of the proposed schemes.     

Structuring product development processes

This paper proposes operational frameworks for structuring product development processes. The primary objective of this research is to develop procedures to minimize iterations during the development process which adversely affect development time and costs. Several procedures are introduced to restructure the development process. The computation of the corresponding product development times is facilitated by two Markov models addressing different types of learning. The methodologies are employed to identify a set of managerial concerns in restructuring the product development processes.The developed framework has become an integral part of a re-engineering project for the development of rocket engines at Rocketdyne Division of Rockwell International. Throughout the paper, the methodologies are illustrated with the help of this process.     

基于隐变量贝叶斯模型的稀疏信号恢复

该文基于贝叶斯分析的视角,揭示了一类算法,包括使用隐变量模型的稀疏贝叶斯学习(SBL),正则化FOCUSS算法以及Log-Sum算法之间的内在关联。分析显示,作为隐变量贝叶斯模型的一种,稀疏贝叶斯学习使用第2类最大似然(Type II ML)在隐变量空间进行运算,可以视作一种更为广义和灵活的方法,并且为不适定反问题的稀疏求解提供了改进的途径。较之于目前基于第1类最大似然(Type I ML)的稀疏方法,仿真实验证实了稀疏贝叶斯学习的优越性能。     

非全日制研究生线上线下混合式教学模式研究 ——以《现代电气控制技术》为例

随着教育信息化技术的发展，线上线下混合式教学模式已成为一种趋势。为了解决非全日制研究生课堂教学召集困难、效果不佳等问题，提出了基于“互联网＋虚拟仿真技术”的线上线下混合式教学模式。本文以控制工程专业学位研究生为例，结合《现代电气控制技术》课程，探讨了线上线下混合式教学实现途径、师生互动方法、项目驱动案例教学法以及电气控制系统虚拟仿真实验平台的构建方法，切实提升非全日制研究生的培养质量。     

基于集成 PU 学习数据流分类的入侵检测方法

入侵检测问题可以模型化为数据流分类问题,传统的数据流分类算法需要标注大量的训练样本,代价昂贵,降低了相关算法的实用性。在PU学习算法中,仅需标注部分正例样本就可以构造分类器。对此本文提出一种动态的集成PU学习数据流分类的入侵检测方法,只需要人工标注少量的正例样本,就可以构造数据流分类器。在人工数据集和真实数据集上的实验表明,该方法具有较好的分类性能,在处理偏斜数据流上优于三种PU 学习分类方法,并具有较高的入侵检测率。     

经典电路实验翻转课堂教学模式的设计

以经典电路实验课程《RC过渡电路性能的验证》为例，给出了其翻转课堂教学模式的设计。课前以网络平台为载体推送学习资料，课上测试合格的学生才被允许进行实验，实验前给出启发式问题，实验后组织学生分组讨论，教师可针对学生的学习情况进行个性化指导，实现了自主学习+沉浸性操作+个性化教育的学习模式。教学实践情况表明，翻转课堂有效解决了实验学时不足的难题，效果良好。     

Experimental Validation of Entropy-Driven Swarm Exploration under Sparsity Constraints with Sparse Bayesian Learning

Increasing the autonomy of multi-agent systems or swarms for exploration missions requires tools for efficient information gathering. This work studies this problem from theoretical and experimental perspectives and evaluates an exploration system for multiple ground robots that cooperatively explore a stationary spatial process. For the distributed model, two conceptually different distribution paradigms are considered. The exploration is based on fusing distributively gathered information using Sparse Bayesian Learning (SBL), which permits representing the spatial process in a compressed manner and thus reduces the model complexity and communication load required for the exploration. An entropy-based exploration criterion is formulated to guide the agents. This criterion uses an estimation of a covariance matrix of the model parameters, which is then quantitatively characterized using a D-optimality criterion. The new sampling locations for the agents are then selected to minimize this criterion. To this end, a distributed optimization of the D-optimality criterion is derived. The proposed entropy-driven exploration is then presented from a system perspective and validated in laboratory experiments with two ground robots. The experiments show that SBL together with the distributed entropy-driven exploration is real-time capable and leads to a better performance with respect to time and accuracy compared with similar state-of-the-art algorithms.     

Systems thinking approaches for international green chemistry education

1. Download : Download high-res image (133KB)
2. Download : Download full-size image

     

Spatio-temporal metric learning for individual recognition from locomotion

Individual recognition from locomotion is a challenging task owing to large intra-class and small inter-class variations. In this article, we present a novel metric learning method for individual recognition from skeleton sequences. Firstly, we propose to model articulated body on Riemannian manifold to describe the essence of human motion, which can reflect biometric signatures of the enrolled individuals. Then two spatia-temporal metric learning approaches are proposed, namely Spatio-Temporal Large Margin Nearest Neighbor (ST-LMNN) and Spatio-Temporal Multi-Metric Learning (STMM), to learn discriminant bilinear metrics which can encode the spatio-temporal structure of human motion. Specifically, the ST-LMNN algorithm extends the bilinear model into classical Large Margin Nearest Neighbor method, which learns a low-dimensional local linear embedding in the spatial and temporal domain, respectively. To further capture the unique motion pattern for each individual, the proposed STMM algorithm learns a set of individual-specific spatio-temporal metrics, which make the projected features of the same person closer to its class mean than that of different classes by a large margin. Beyond that, we present a new publicly available dataset for locomotion recognition to evaluate the influence of both internal and external covariant factors. According to the experimental results from the three public datasets, we believe that the proposed approaches are both able to achieve competitive results in individual recognition.