A Spurious Equilibria-free Learning Algorithm for the Blind Separation of Non-zoer Skewness Signals

We present a new learning algorithm for the blind separation of independent source signals having non-zero skewness (the 3rd-order cumulant) (the source signals have non-symmetric probability distribution.), from their linear mixtures. It is shown that for a class of source signals whose probability distribution functions is not symmetric, a simple adaptive learning algorithm using quadratic function (f(x)=x²) is very efficient for blind source separation task. It is proved that all stable equilibria of the proposed learning algorithm are desirable solutions. Extensive computer simulation experiments confirmed the validity of the proposed algorithm.     

Incremental Feature Selection

Feature selection is a problem of finding relevant features. When the number of features of a dataset is large and its number of patterns is huge, an effective method of feature selection can help in dimensionality reduction. An incremental probabilistic algorithm is designed and implemented as an alternative to the exhaustive and heuristic approaches. Theoretical analysis is given to support the idea of the probabilistic algorithm in finding an optimal or near-optimal subset of features. Experimental results suggest that (1) the probabilistic algorithm is effective in obtaining optimal/suboptimal feature subsets; (2) its incremental version expedites feature selection further when the number of patterns is large and can scale up without sacrificing the quality of selected features.     

Learning Dextrous Manipulation Skills for Multifingered Robot Hands Using the Evolution Strategy

We present a method for autonomous learning of dextrous manipulation skills with multifingered robot hands. We use heuristics derived from observations made on human hands to reduce the degrees of freedom of the task and make learning tractable. Our approach consists of learning and storing a few basic manipulation primitives for a few prototypical objects and then using an associative memory to obtain the required parameters for new objects and/or manipulations. The parameter space of the robot is searched using a modified version of the evolution strategy, which is robust to the noise normally present in real-world complex robotic tasks. Given the difficulty of modeling and simulating accurately the interactions of multiple fingers and an object, and to ensure that the learned skills are applicable in the real world, our system does not rely on simulation; all the experimentation is performed by a physical robot, in this case the 16-degree-of-freedom Utah/MIT hand. Experimental results show that accurate dextrous manipulation skills can be learned by the robot in a short period of time. We also show the application of the learned primitives to perform an assembly task and how the primitives generalize to objects that are different from those used during the learning phase.     

Learning from Innate Behaviors: A Quantitative Evaluation of Neural Network Controllers

The aim was to investigate a method of developing mobile robot controllers based on ideas about how plastic neural systems adapt to their environment by extracting regularities from the amalgamated behavior of inflexible (nonplastic) innate subsystems interacting with the world. Incremental bootstrapping of neural network controllers was examined. The objective was twofold. First, to develop and evaluate the use of prewired or innate robot controllers to bootstrap backpropagation learning for Multilayer Perceptron (MLP) controllers. Second, to develop and evaluate a new MLP controller trained on the back of another bootstrapped controller. The experimental hypothesis was that MLPs would improve on the performance of controllers used to train them. The performances of the innate and bootstrapped MLP controllers were compared in eight experiments on the tasks of avoiding obstacles and finding goals. Four quantitative measures were employed: the number of sensorimotor loops required to complete a task; the distance traveled; the mean distance from walls and obstacles; the smoothness of travel. The overall pattern of results from statistical analyses of these quantities supported the hypothesis; the MLP controllers completed the tasks faster, smoother, and steered further from obstacles and walls than their innate teachers. In particular, a single MLP controller incrementally bootstrapped by a MLP subsumption controller was superior to the others.     

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。