Connectionist Models of Orientation Identification

We have used connectionist simulations in an attempt to understand how orientation tuned units similar to those found in the visual cortex can be used to perform psychophysical tasks involving absolute identification of stimulus orientation. In one task, the observer (or the network) was trained to identify which of two possible orientations had been presented, whereas in a second task there were 10 possible orientations that had to be identified. By determining asymptotic performance levels with stimuli separated to different extents it is possible to generate a psychophysical function relating identification performance to stimulus separation. Comparisons between the performance functions of neural networks with those found for human subjects performing equivalent tasks led us to the following conclusions. Firstly, we found that the ‘psychometric functions’ generated for the networks could accurately mimic the performance of the human observers. Secondly, the most important orientation selective units in such tasks are not the most active ones (as is often assumed). Rather, the most important units were those selective for orientations offset 15° to 20° to either side of the test stimuli. Such data reinforce recent psychophysical and neurophysiological data suggesting that orientation coding in the visual cortex should be thought of in terms of distributed coding. Finally, if the same set of input units was used in the two-orientation and the 10-orientation situation, it became apparent that in order to explain the difference in performance in the two cases it was necessary to use either a network without hidden units or one with a very small number of such units. If more hidden units were available, performance in the 10-orientation case was found to be too good to fit the human data. Such results cast doubt on the hypothesis that hidden units need to be trained in order to account for simple perceptual learning in humans.     

Integrating Neural and Symbolic Approaches: A Symbolic Learning Scheme for a Connectionist Associative Memory

This paper deals with the integration of neural and symbolic approaches. It focuses on associative memories where a connectionist architecture tries to provide a storage and retrieval component for the symbolic level. In this light, the classic model for associative memory, the Hopfield network is briefly reviewed. Then, a new model for associative memory, the hybrid Hopfield-clique network is presented in detail. Its application to a typically symbolic task, the post -processing of the output of an optical character recognizer, is also described. In the author's view, the hybrid Hopfield -clique network constitutes an example of a successful integration of the two approaches. It uses a symbolic learning scheme to train a connectionist network, and through this integration, it can provide perfect storage and recall. As a conclusion, an analysis of what can be learned from this specific architecture is attempted. In the case of this model, a guarantee for perfect storage and recall can only be given because it was possible to analyze the problem using the well-defined symbolic formalism of graph theory. In general, we think that finding an adequate formalism for a given problem is an important step towards solving it.     

Increasing the Power of Connectionist Networks (CN) by Improving Structures,Processes, Learning

A crucial dilemma is how to increase the power of connectionist networks (CN), since simply increasing the size of today's relatively small CNs often slows down and worsens learning and performance. There are three possible ways: (1) use more powerful structures; (2) increase the amount of stored information, and the power and the variety of the basic processes; (3) have the network modify itself (learn, evolve) in more powerful ways. Today's connectionist networks use only a few of the many possible topological structures, handle only numerical values using only very simple basic processes, and learn only by modifying weights associated with links. This paper examines the great variety of potentially muck more powerful possibilities, focusing on what appear to be the most promising: appropriate brain-like structures (e.g. local connectivity, global convergence and divergence); matching, symbol-handling, and list-manipulating capabilities; and learning by extraction-generation-discovery.     

Symbol Grounding or the Emergence of Symbols? Vocabulary Growth in Children and a Connectionist Net

The Symbolic Grounding Problem is viewed as a by-product of the classical cognitivist approach to studying the mind. In contrast, an epigenetic interpretation of connectionist approaches to studying the mind is shown to offer an account of symbolic skills as an emergent, developmental phenomenon. We describe a connectionist model of concept formation and vocabulary growth that auto-associates image representations and their associated labels. The image representations consist of clusters of random dot figures, generated by distorting prototypes. Any given label is associated with a cluster of random dot figures. The network model is tested on its ability to reproduce image representations given input labels alone (comprehension) and to identify labels given input images alone (production). The model implements several well-documented findings in the literature on early semantic development; the occurrence of over- and under-extension errors; a vocabulary spurt; a comprehension/production asymmetry; and a prototype effect. It is shown how these apparently disparate findings can be attributed to the operation of a single underlying mechanism rather than by invoking separate explanations for each phenomenon. The model represents a first step in the direction of providing a formal explanation of the emergence of symbolic behaviour in young children.     

A defence of functional modularity

Although belief in the existence of mental modules of some form is widespread among cognitive researchers, neurally sophisticated researchers commonly resist the view that cognitive processing involves modules that are functionally independent of one another. Moreover, within the past few years, at least three noted researchers (Fodor, Kosslyn and Uttal) have called into serious question the existence of distinct modules in broad areas of human cognition. This paper offers a defence of the existence of functionally independent modules, which, though spatially distributed, communicate via traditionally conceived input/output channels. This defence proceeds: (i) by showing that the anti-modularity arguments of Fodor, Kosslyn and Uttal are not compelling; (ii) by presenting theoretically-grounded reasons why any connectionist is committed, via the most basic tenets of connectionism, to accepting the existence of functionally independent modules; (iii) by presenting holistically inclined connectionists with a novel challenge, namely, to demonstrate that a single, holistic network could display strong levels of generalization as a side-effect of multiple, previously acquired skills. In the course of these arguments, I examine a recent generalization challenge posed by Phillips (2000, Connection Science, 12: 1–19) to eliminative connectionists.     

Selecting an artificial neural network for efficient modeling and accurate simulation of the milling process

In this paper, two supervised neural networks are used to estimate the forces developed during milling. These two Artificial Neural Networks (ANNs) are compared based on a cost function that relates the size of the training data to the accuracy of the model. Training experiments are screened based on design of experiments. Verification experiments are conducted to evaluate these two models. It is shown that the Radial Basis Network model is superior in this particular case. Orthogonal design and specifically equally spaced dimensioning showed to be a good way to select the training experiments.     

基于数值模拟的多型腔注射模浇注系统优化设计

基于数值模拟基础,针对多型腔注射模的结构特点,以流道尺寸为变量,以节能为目标进行浇注系统的优化设计。设计了模具优化的数学模型,有效利用注塑机,增大浇注系统压力,优化流道截面尺寸,减小流道凝料,节约原材料,有效降低锁模力,缩短充模时间,提高了生产效率。     

BP神经网络在压铸模优化设计中的应用

简述了在压铸过程中飞边产生的原因和相应的预防措施以及BP人工神经网络的基本原理和算法,利用BP人工神经网络来预测压铸件飞边的大小,从而达到优化于压铸模设计的目的。     

Cyclic Behaviour of Autonomous,Synchronous Boolean Networks: Some Theorems and Conjectures

In order to synthesize neural network structures with specific capabilities, a predictive theoretical model of the network configuration-behaviour relationship is needed. The problem is a very complex one and has been addressed by very few researchers. This paper considers just one fundamental logical feature, achievable cycle lengths, of very simple autonomous, synchronous, polyfunctional Boolean networks. The lack of a predictive theoretical model for the relationship between network configuration and cyclic behaviour is discussed, and some simulation results are reported. Several theorems and conjectures on the effect of connectivity restrictions on achievable cycle lengths are presented. The conjectures presented remain, thus far, unproven; the process of exploring possible methods for their proofs, or proofs of their unprovability, will provide insight into methods, and possibilities, of modelling many other aspects of network configuration-behaviour relationships.     

基于数值模拟的铝合金壳体浇注系统优化设计

针对铝合金壳体的结构特点,应用UG软件设计了浇注系统方案一,并应用铸造分析软件Any casting对熔融铝合金液充型和凝固过程进行了模拟,通过模拟结果判断方案一的优缺点,设计了优化的浇注系统方案二和方案三,通过比较得到了优化的浇注系统进料位置和进料方式,对成型零件的质量有很重要影响。     

人工神经网络预测屈服强度

在实验数据的基础上,采用附加动量项和变步长的方法,对人工神经网络的BP算法进行了训练。利用训练后所得到的模型,对屈服强度进行了分析和预测。计算表明,网络预测值与实测值之间具有很高的相关性和精确度,为屈服强度提供了一定的理论辅助手段。     

Application of neural computing in basic oxygen steelmaking

The use of computer control in the basic oxygen steelmaking (BOS) process is essential to obtain accurate end-point temperature (EPT) and carbon control in liquid steel. The current computer model employed to execute this task is a procedural model that must be maintained by a person with considerable steelmaking knowledge. The requirement for an improved, maintenance reduced model is becoming increasingly important as expertise in this area is dwindling. The steelmaking process is highly complex and volatile. Artificial neural networks (ANNs) have been used to model this type of non-linear system. This paper describes an investigation into the use of ANNs to predict oxygen and coolant requirements during the end-blow period of the steelmaking process. During the end-blow period, a temperature measurement and sample are taken using a probe. These measurements are then used as inputs to the ANN model in order to predict how much oxygen to blow and how much coolant to add in order to achieve the desired end-point conditions in the steel at the end of the process. The software used to perform most of the modelling was the Clementine Data Mining System. This paper discusses the results from the ANN trials at Port Talbot BOS plant, which is part of the Corus Group.     

Automated detection and quantification of hidden voids in triplex bonding layers using active lock-in thermography

This paper presents an automated hidden void detection and quantification technique for inspecting triplex bonding layers in liquefied natural gas (LNG) carriers using active lock-in thermography. Hidden voids are first detected and visualized by an amplitude image and a series of binary image processing. Then, the sizes of the detected voids are quantified using an empirical mapping function, relating the detected void sizes to the void sizes obtained by an independent X-ray testing. The performance of the proposed technique is blind tested using two triplex specimens. The experimental results reveal that the hidden voids can be successfully detected and quantified.     

Impedance inversion in eddy current testing of layered planar structures via neural networks

The inversion of eddy current probe impedance measurements is widely recognized as a complex theoretical problem whose solution is likely to have a significant impact on the characterization of materials. In this paper the evaluation of the conductivity profile of a layered planar structure is performed after inverting the impedance of a circular air-cored probe coil, of rectangular cross-section, using multilayer perceptron neural networks, trained via the back propagation learning algorithm. The merits of the method are illustrated in the light of two engineering examples.     

Neural Network Music Composition by Prediction: Exploring the Benefits of Psychoacoustic Constraints and Multi-scale Processing

In algorithmic music composition, a simple technique involves selecting notes sequentially according to a transition table that specifies the probability of the next note as a function of the previous context. An extension of this transition-table approach is described, using a recurrent autopredictive connectionist network called CONCERT. CONCERT is trained on a set of pieces with the aim of extracting stylistic regularities. CONCERT can then be used to compose new pieces. A central ingredient of CONCERT is the incorporation of psychologically grounded representations of pitch, duration and harmonic structure. CONCERT was tested on sets of examples artificially generated according to simple rules and was shown to learn the underlying structure, even where other approaches failed. In larger experiments, CONCERT was trained on sets of J. S. Bach pieces and traditional European folk melodies and was then allowed to compose novel melodies. Although the compositions are occasionally pleasant, and are preferred over compositions generated by a third-order transition table, the compositions suffer from a lack of global coherence. To overcome this limitation, several methods are explored to permit CONCERT to induce structure at both fine and coarse scales. In experiments with a training set of waltzes, these methods yielded limited success, but the overall results cast doubt on the promise of note-by-note prediction for composition.     

基于BP人工神经网络的TC17钛合金显微组织-力学性能关系预测

钛合金的性能对其组织状态十分敏感，与组织的多种显微特征呈现非线性的交互关系。本研究在定量分析钛合金显微组织的基础上，采用BP人工神经网络方法建立了TC17钛合金组织与力学性能的关系模型。该模型输入的显微组织特征参数包括：α相体积分数、α相厚度和不同形态α相的体积分数，输出的力学性能包括抗拉强度、屈服强度、延伸率和断面收缩率。结果表明，该模型具有很好的预测精度和泛化能力。应用贝叶斯正则化和动量梯度下降学习法较好地解决了传统BP人工神经网络训练高精度和预测低精度的过拟合现象。此模型的建立对构建TC17合金利用组织预报力学性能的专家知识库具有重要作用，而且对钛合金专家系统的整体开发具有重要指导意义。     

人工神经网络在预测斜轧穿孔毛管偏差中的应用

斜轧穿孔中毛管质量与许多工艺参数，如辊型，送进角，顶头前伸量及温度，以及设备性能参数如穿孔机刚度，加工精度和顶杆振动等有关。传统的轧制理论难以解决其质量问题，应用人工神经网络则能较好地解决毛管质量的预测问题，应用实测的工艺参数与其对应的毛管精度参数，训练和学习网络的权值和阈值，建立起模拟穿孔机生产的数学模型，即网络模型，预测了毛管偏差及合理的工艺参数。     

Research on image segmentation of weld seam of oil derrick welded by arc welding robot

This paper puts forward a new method of PCNN (pulse-coupled neural networks) image segmentation, in which the binary matrix of the ignition frequency matrix is employed, for the first time, to act as the final result of image segmentation. It gives the principles of PCNN parameter selection under the guidance of this process. The new method reduces the dependence of PCNN on parameters, improves the effect of image segmentation, and produces good results after being applied to image recognition of weld seam of oil derrick welded by arc welding robot.     

深度卷积神经网络在移动机器人的应用研究

闭环检测是移动机器人自主导航以及各种视觉定位的重要组成。近年来随着深度卷积神经网络展,基于卷积描述符的闭环检测与基于手工设计描述符的闭环检测,均在各个系统得到了应用。通过利用深度卷积神经网络实现图像匹配,并将其用于移动机器人的全局定位算法中,对其工程实际表现进行了定量评估以及对比。从所设计的试验方法量化对比出目前主流的描述符在各种场景应用中的优劣性,可知基于AlexNet模型的卷积描述符在各实验中均表现最佳,为图像匹配及其全局定位提供定量参考选择标准。