Sensor Fusion System Using Recurrent Fuzzy Inference

In robotic and manufacturing systems, it is difficult to measure the state of systems accurately because of many uncertain factors and noise, and it is very important to estimate the state of systems. We must measure the phenomena of systems by multiple sensors and estimate the state of systems by acquiring information of sensors. However, we can not acquire all of sensor information synchronically, because each sensor has particular sensor information and measuring time. For estimating the state of systems by multiple sensors, a multi-sensor fusion system fusing various sensory information is needed. In this paper, we propose a Recurrent Fuzzy Inference (RFI) with recurrent inputs and apply it to a multi-sensor fusion system for estimating the state of systems. The membership functions of RFI are expressed by Radial Basis Function (RBF) with insensitive ranges. The shape of the membership functions can be adjusted by a learning algorithm. The learning algorithm is based on the steepest descent method and incremental learning which can add new fuzzy rules. The effectiveness of the multi-sensor fusion system using RFI will be shown through a numerical experiment of moving robot and estimation of surface roughness in grinding process.     

Collinearity and Parallelism are Statistically Significant Second-Order Relations of Complex Cell Responses

By investigating the second-order statistics of Gabor wavelet responses derived from natural images, we show that collinearity and parallelism are conspicuous relations. We give a precise mathematical characterization of these Gestalt principles by the conditional probability of two responses. Essential for our investigations is a non-linear transformation, initially utilized within the object recognition system [5], which transforms continuous Gabor wavelet responses into a binary code indicating the presence or absence of local oriented line segments.     

A Neuro-fuzzy Coding for Processing Incomplete Data: Application to the Classification of Seismic Events

This letter presents a method for modelling and processing incomplete data in connectionist systems. The approach consists in applying a neuro-fuzzy coding to the input data of a neural network. After an introduction to the different kinds of imperfections, we propose a neuro-fuzzy coding in order to take incomplete data into account. We show the efficiency of this coding on the problem of the classification of seismic events. The results show that a neuro-fuzzy coding of the inputs of a neural network increases the performance and classifies incomplete data with little affect on the results.     

Conjectural Equilibrium in Multiagent Learning

Learning in a multiagent environment is complicated by the fact that as other agents learn, the environment effectively changes. Moreover, other agents' actions are often not directly observable, and the actions taken by the learning agent can strongly bias which range of behaviors are encountered. We define the concept of a conjectural equilibrium, where all agents' expectations are realized, and each agent responds optimally to its expectations. We present a generic multiagent exchange situation, in which competitive behavior constitutes a conjectural equilibrium. We then introduce an agent that executes a more sophisticated strategic learning strategy, building a model of the response of other agents. We find that the system reliably converges to a conjectural equilibrium, but that the final result achieved is highly sensitive to initial belief. In essence, the strategic learner's actions tend to fulfill its expectations. Depending on the starting point, the agent may be better or worse off than had it not attempted to learn a model of the other agents at all.     

基于模糊推理的均热炉温度迭代学习控制研究

根据均热炉装钢的初值条件，基于模糊推理基本理论，获得温度控制的前馈量，构成知识库，利用迭代学习算法，修正前次迭代输入的前馈量。在烧钢加热过程中，采用前馈、反馈与迭代学习算法相结合的控制方案。     

异地计算机教学与训练系统的结构模型研究

异地计算机教学与训练系统就是利用计算机网络环境，向分布在异地的授课者和学习者提供一种模拟面对面教学和训练的虚拟环境。     

基于进化规划的神经网络群的设计方法

提出一种基于进化规划的神经网络群的自动设计方法．该方法不仅使得神经网络群中的个体网络倾向于完成不同的子任务，同时各神经网络个体在进化过程中不断寻找最好的协作关系，而且神经网络群的规模和结构不需预先设定．仿真试验表明，该算法是有效的。     

求解部分可观测马氏决策过程的强化学习算法

针对部分可观测马氏决策过程(POMDP)中，由于感知混淆现象的存在，利用Sarsa等算法得到的无记忆策略可能发生振荡的现象，研究了一种基于记忆的强化学习算法——CPnSarsa(λ)学习算法来解决该问题．它通过重新定义状态，Agent结合观测历史来识别混淆状态．将CPnSarsa(λ)算法应用到一些典型的POMDP，最后得到的是最优或近似最优策略，与以往算法相比，该算法的收敛速度有了很大提高．     

采样算子调整的径向基网络增量映射学习算法

为了提高增量映射学习(IPL)算法的效率,调整了径向基神经网络基函数的中心及方差,以达到调整采样算子的目的,同时,通过神经元函数相关性的计算,确定添加新神经元时,相关函数的阈值,为系统结构调整提供相应依据.新方法步骤相对简单,所以算法速度较快;仿真结果表明,由于系统参数得到调整,对于同一问题,改进IPL算法得到的径向基神经网络结构较一般算法得到的网络结构简单,输出结果也较为精确.     

多示例学习及其研究现状

较全面地介绍和分析了第4种机器学习框架的多示例学习(MIL)．首先通过数学表达式对多示例学习进行描述，概括了其主要性质；然后总结了目前主要的求解多示例学习问题的算法，剖析了这些算法的主要思想；最后对多示例学习的未来发展作了展望．