Experiments of Fast Learning with High Order Boltzmann Machines

This work reports the results obtained with the application of High Order Boltzmann Machines without hidden units to construct classifiers for some problems that represent different learning paradigms. The Boltzmann Machine weight updating algorithm remains the same even when some of the units can take values in a discrete set or in a continuous interval. The absence of hidden units and the restriction to classification problems allows for the estimation of the connection statistics, without the computational cost involved in the application of simulated annealing. In this setting, the learning process can be sped up several orders of magnitude with no appreciable loss of quality of the results obtained.     

神经网络离散变结构控制的算法及其应用

本文首次将自适应线性神经元（Ａｄａｌｉｎｅ）用于离散变结构控制。以滑模面Ｓ（ｋ）＝０作为Ａｄａｌｉｎｅ元的希望输出，作为Ａｄａｌｉｎｅ元的实际输出，通过ＬＭＳ算法在线调整权值可保证滑态可达条件的满足。应用所提出的控制策略对泵控马达速度伺服系统进行控制，仿真表明控制效果是令人满意的。     

A combined queueing network and stochastic Petri-net approach for evaluating the performability of fault-tolerant computer systems

In this paper the performability analysis of fault-tolerant computer systems using a hierarchical decomposition technique is presented. A special class of queueing network (QN) models, the so-called BCMP [4], and generalized stochastic Petri nets (GSPN) [1] which are often used to separately model performance and reliability respectively, have been combined in order to preserve the best modelling features of both.

A conceptual model is decomposed into GSPN and BCMP submodels, which are solved in isolation. Then, the remaining GSPN portion of the model is aggregated with flow-equivalents of BCMP models, in order to compute performability measures. The substitutes of BCMP models are presented by means of simple GSPN constructs, thereby preserving the 1st and 2nd moments of the throughput. A simple example of a data communication system where failed transmissions are corrected, is presented.     

Fault-accommodation with intelligent sensors

Optimal sensor fault-accommodation is considered for faults modelled by an increase in measurement noise. This noise is taken to be bounded and its probabilistic properties unknown. It is assumed that intelligent (e.g. self-validating) instrumentation is in use and estimates of the noise bounds are available. The fault-tolerant controller is designed to optimize a noise rejection and a nominal reference tracking index and leads to a mixed norm minimization problem (l₁/l₂). We exploit known results and a particular feedback configuration to show that it is possible to optimize simultaneously without a trade-off the two performance indices. The results are applied to systems where the presence of auxiliary measurements allows for an optimal fault-accommodation strategy. Using properties of the optimal solution, we define a factorization for the optimal controller alternative to the Youla parametrization, leading to an algorithm which is optimal, transparent and efficient.     

以EMD作基础的氧化锰制成湿度敏感器的新技术

最近国外报道把ＥＭＤ粉末等制成湿度敏感器的技术，但对其作用机理的解释尚有欠妥之处，本文除简介此类湿度敏感器的工艺之外，还利用我们研究水蒸气对ＥＭＤｏＡ附的理论予以阐释，并确认其合理与否     

A knowledge-based system for sensor selection

This paper presents a Knowledge-based system (KBS) developed to allow users, who may not be knowledgeable about sensors, to select sensors suitable for their specific needs. The KBS runs on a micro-computer. The selection criteria are user specified and are based on the desired measurement parameters. The system output includes all of the operational and dimensional parameters of the recommended sensor, price, and vendor information.     

Bioprocess applications of model-based estimation techniques

The last decade has seen the development of a number of approaches for estimating those variables which are difficult to measure on-line in industrial process situations. Whilst a range of techniques is available, a common element is the use of process knowledge in the form of a system model. In the case of bioprocess systems, although a large range of models has been presented in the literature, their use in estimation schemes on an industrial scale has been limited. A number of reasons can be identified for their low level of utilisation. Of particular significance is the uncertainty which exists in quantifying system performance and the process-model mismatch which inevitably results. The level of ‘pre-defined model’ uncertainty, together with the knowledge gained during the course of the fermentation, serves to dictate estimator structure. The paper considers a range of estimation strategies and contrasts, through industrial applications, their performance characteristics and utility.     

Application of artificial neural networks to the analysis of two‐dimensional fluorescence spectra in recombinant E coli fermentation processes

A two‐dimensional (2D) spectrofluorometer was used to monitor various fermentation processes with recombinant E coli for the production of 5‐aminolevulinic acid (ALA). The whole fluorescence spectral data obtained during a process were analyzed using artificial neural networks, ie self‐organizing map (SOM) and feedforward backpropagation neural network (BPNN). The SOM‐based classification of the whole spectral data has made it possible to qualitatively associate some process parameters with the normalized weights and variances, and to select some useful combinations of excitation and emission wavelengths. Based on the classified fluorescence spectra a supervised BPNN algorithm was used to predict some of the process parameters. It was also shown that the BPNN models could elucidate some sections of the process's performance, eg forecasting the process's performance. Copyright © 2005 Society of Chemical Industry     

Linearly many faults in Cayley graphs generated by transposition trees

We prove that when linearly many vertices are deleted in a Cayley graph generated by a transposition tree, the resulting graph has a large connected component containing almost all remaining vertices.