有教师的线性基本函数前向三层神经网络结构研究

优化选择隐节点数是人们在应用基于误差反传算法的有教师的线性基本函数前向三层神经网络过程中首先遇到的一个十分重要而又困难的问题。本文从国内外大量应用裕列中陪结归纳出了一个初定这种网络隐节点数的经验公式，提出了一种判断所选隐节点数是否多余的具体方法，并从理论上做了详细的推导。     

Queueing Petri nets with product form solution

The product form results recently published for stochastic Petri nets are combined with the well-known product form results for queueing networks in the model formalism of queueing Petri nets yielding the class of product form queueing Petri nets. This model class includes stochastic Petri nets with product form solution and BCMP queueing networks as special cases. We introduce an arrival theorem for the model class and present an exact aggregation approach extending known approaches from queueing networks.     

Interactive structural learning of Bayesian networks

We propose an hybrid approach for structure learning of Bayesian networks, in which a computer system and a human expert cooperate to search for the best structure. The system builds an initial tree structure which is graphically presented to the expert, and then the expert can modify this structure according to his knowledge of the domain. The system has several tools for aiding the human in this task: it allows for graphical editing (adding, deleting, inverting arcs) of the network, it shows graphically the correlation between variables, and it gives a measure of the quality and complexity for each structure. A measure which combines both quality and complexity, that we call quality, is defined. We have tested the tool in two domains: atmospheric pollution and car insurance, with good results.     

Spanning tree-based genetic algorithm for bicriteria transportation problem

In this paper, we present a new approach which is spanning tree-based genetic algorithm for bicriteria transportation problem. The transportation problem have the special data structure in solution characterized as a spanning tree. In encoding transportation problem, we introduce one of node encoding which is adopted as it is capable of equally and uniquely representing all possible basic solutions. The crossover and mutation was designed based on this encoding. And we designed the criterion that chromosome always feasibility converted to a transportation tree. In the evolutionary process, the mixed strategy and roulette wheel selection is used. Numerical experiments will be shown the effectiveness and efficiency of the proposed algorithm.     

Neural networks of data inhibiting long memory pattern

We experiment with three neural network models for forecasting to better understand the performance of neural networks for the case when the data exhibits a long memory pattern. To obtain the optimum networks, the effect of network characteristics such as the training parameters, the number of hidden layers, and the testing and training percentages are simulated. The third model, which consists of a combination of individual time series forecasts, provides superior results.     

Modeling users through an expert system and a neural network

With the number of Internet and Web users increasing rapidly, electronic service providers are competing to satisfy and better serve customers looking for information or channels of advertisement. A wide variety of browses, specialized sites, custom made software, etc. are being offered on a regular basis. However, the user has to filter through a large number of files before finding what he/she is really looking for. This paper presents a user modeling expert system, SIGMA, based on neural networks for encapsulating Internet and Web users' habits and preferences. SIGMA is an artificial intelligence application designed to answer an Internet client needs and preferences. It analyses the user supplied demographic data and the monitored transactions then generate a tailored profile that is ultimately used to filter what information is being passed on to him/her in an effort to reduce and hopefully eliminate the time and energy expended in sifting through raw and often unwanted data.     

A self-organizing genetic algorithm for multimodal function optimization

A genetic algorithm (GA) has control parameters that must be determined before execution. We propose a self-organizing genetic algorithm (SOGA) as a multimodal function optimizer which sets GA parameters such as population size, crossover probability, and mutation probability adaptively during the execution of a genetic algorithm. In SOGA, GA parameters change according to the fitnesses of individuals. SOGA and other approaches for adapting operator probabilities in GAs are discussed. The validity of the proposed algorithm is verified in simulation examples, including system identification. This work was presented, in part, at the International Symposium on Artificial Life and Robotics, Oita, Japan, February 18–20, 1996     

A review of neural networks for statistical process control

This paper aims to take stock of the recent research literature on application of Neural Networks (NNs) to the analysis of Shewhart's traditional Statistical Process Control (SPC) charts. First appearing in the late 1980s, most of the literature claims success, great or small, in applying NNs for SPC (NNSPC). These efforts are viewed in this paper as useful steps towards automatic on-line SPC for continuous improvement of quality and for real-time manufacturing process control. A standard NN approach that can parallel the universality of the traditional Shewhart charts has not yet been developed or adopted, although knowledge in this area is rapidly increasing. This paper attempts to provide a practical insight into the issues involved in application of NNs to SPC with the hope of advancing the use of NN techniques and facilitating their adoption as a new and useful aspect of SPC. First, a brief review of control chart analysis prior to the introduction of NN technology is presented. This is followed by an examination and classification of the NNSPC existing literature. Next, an extensive discussion of implementation issues with reference to significant research papers is presented. Finally, after summarising the survey, a set of general guidelines for future applications of NNs to SPC is outlined.     

Training a Vision Guided Mobile Robot

This paper presents the design, implementation and evaluation of a trainable vision guided mobile robot. The robot, CORGI, has a CCD camera as its only sensor which it is trained to use for a variety of tasks. The techniques used for training and the choice of natural light vision as the primary sensor makes the methodology immediately applicable to tasks such as trash collection or fruit picking. For example, the robot is readily trained to perform a ball finding task which involves avoiding obstacles and aligning with tennis balls. The robot is able to move at speeds up to 0.8 ms^-1 while performing this task, and has never had a collision in the trained environment. It can process video and update the actuators at 11 Hz using a single $20 microprocessor to perform all computation. Further results are shown to evaluate the system for generalization across unseen domains, fault tolerance and dynamic environments.     

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.