Active symbols and internal models: Towards a cognitive connectionism

In the first section of the article, we examine some recent criticisms of the connectionist enterprise: first, that connectionist models are fundamentally behaviorist in nature (and, therefore, non-cognitive), and second that connectionist models are fundamentally associationist in nature (and, therefore, cognitively weak). We argue that, for a limited class of connectionist models (feed-forward, pattern-associator models), the first criticism is unavoidable. With respect to the second criticism, we propose that connectionist modelsare fundamentally associationist but that this is appropriate for building models of human cognition. However, we do accept the point that there are cognitive capacities for which any purely associative model cannot provide a satisfactory account. The implication that we draw from is this is not that associationist models and mechanisms should be scrapped, but rather that they should be enhanced.In the next section of the article, we identify a set of connectionist approaches which are characterized by active symbols — recurrent circuits which are the basis of knowledge representation. We claim that such approaches avoid criticisms of behaviorism and are, in principle, capable of supporting full cognition. In the final section of the article, we speculate at some length about what we believe would be the characteristics of a fully realized active symbol system. This includes both potential problems and possible solutions (for example, mechanisms needed to control activity in a complex recurrent network) as well as the promise of such systems (in particular, the emergence of knowledge structures which would constitute genuine internal models).     

Using neural networks and GIS to forecast land use changes: a Land Transformation Model

The Land Transformation Model (LTM), which couples geographic information systems (GIS) with artificial neural networks (ANNs) to forecast land use changes, is presented here. A variety of social, political, and environmental factors contribute to the model's predictor variables of land use change. This paper presents a version of the LTM parameterized for Michigan's Grand Traverse Bay Watershed and explores how factors such as roads, highways, residential streets, rivers, Great Lakes coastlines, recreational facilities, inland lakes, agricultural density, and quality of views can influence urbanization patterns in this coastal watershed. ANNs are used to learn the patterns of development in the region and test the predictive capacity of the model, while GIS is used to develop the spatial, predictor drivers and perform spatial analysis on the results. The predictive ability of the model improved at larger scales when assessed using a moving scalable window metric. Finally, the individual contribution of each predictor variable was examined and shown to vary across spatial scales. At the smallest scales, quality views were the strongest predictor variable. We interpreted the multi-scale influences of land use change, illustrating the relative influences of site (e.g. quality of views, residential streets) and situation (e.g. highways and county roads) variables at different scales.     

改进BP3参数对网络识别能力影响的研究

分别从BP网络的学习步长,学习速率自适应调整算法的参数,动量法和自适应学习速率结合起来算法的参数3方面讨论了改进BP参数对网络识别能力的影响;在确定BP网络的隐含层节点个数的过程中提出了BP神经网络自适应学习算法,使得隐层节点的选取动态实现。仿真实验表明,该改进是可行的。     

Adaptive smart card-based pull control systems in context-aware manufacturing systems: Training a neural network through multi-objective simulation optimization

Nowadays, context aware manufacturing systems offer interesting capabilities to improve the performance of pull controlled production systems. Smart Kanbans can be used instead of physical cards, and the information become available about the production context, collected for example through sensors and RFID. Such information can be exploited by intelligent pull control strategies so as to dynamically adapt the number of cards. This is particularly useful for production systems that are subjected to unpredictable changes in the customers’ demand, and need to react quickly to preserve a high level of performance. For this reason, we aim, in this article, at proposing an intelligent system, which can communicate with the information system, whose purpose is to autonomously decide or to help managers in adding or removing cards. In this respect, we propose an approach that uses a neural network which is trained offline, directly from simulation, to decide when it is relevant to change the number of cards, and at what production stage. The learning process, based on multi-objective simulation optimization, aims at reducing the production costs as well as the number of changes to avoid nervousness. The use of stochastic simulation, allows various types of complex problems, related to manufacturing systems, to be addressed and fluctuating demand phenomena to be taken into account. The relevance of our approach is illustrated using six published adaptive ConWIP and Kanban systems. Comparisons with adaptive Kanban and ConWIP systems show that the neural network can automatically learn very relevant knowledge. Good results are obtained in terms of performance, with fewer changes in the number of cards. Several possible future research directions are pointed out.     

GSETSK: a generic self-evolving TSK fuzzy neural network with a novel Hebbian-based rule reduction approach

Takagi–Sugeno–Kang (TSK) fuzzy systems have been widely applied for solving function approximation and regression-centric problems. Existing dynamic TSK models proposed in the literature can be broadly classified into two classes. Class I TSK models are essentially fuzzy systems that are limited to time-invariant environments. Class II TSK models are generally evolving systems that can learn in time-variant environments. This paper attempts to address the issues of achieving compact, up-to-date fuzzy rule bases and interpretable knowledge bases in TSK models. It proposes a novel rule pruning method which is simple, computationally efficient and biologically plausible. This rule pruning algorithm applies a gradual forgetting approach and adopts the Hebbian learning mechanism behind the long-term potentiation phenomenon in the brain. It also proposes a merging approach which is used to improve the interpretability of the knowledge bases. This approach can prevent derived fuzzy sets from expanding too many times to protect their semantic meanings. These two approaches are incorporated into a generic self-evolving Takagi–Sugeno–Kang fuzzy framework (GSETSK) which adopts an online data-driven incremental-learning-based approach.Extensive experiments were conducted to evaluate the performance of the proposed GSETSK against other established evolving TSK systems. GSETSK has also been tested on real world dataset using the high-way traffic flow density and Dow Jones index time series. The results are encouraging. GSETSK demonstrates its fast learning ability in time-variant environments. In addition, GSETSK derives an up-to-date and better interpretable fuzzy rule base while maintaining a high level of modeling accuracy at the same time.     

Realization of emergent behavior in collective autonomous mobile agents using an artificial neural network and a genetic algorithm

This paper proposes a pursuit system that utilizes the artificial life concept where autonomous mobile agents emulate the social behavior of animals and insects and realize their group behavior. Each agent contains sensors to perceive other agents in several directions, and decides its behavior based on the information obtained by these sensors. In this paper, a neural network is used for behavior decision controlling. The input of the neural network is decided by the existence of other agents, and the distance to the other agents. The output determines the directions in which the agent moves. The connection weight values of this neural network are encoded as genes, and the fitness individuals are determined using a genetic algorithm. Here, the fitness values imply how much group behavior adequately fit the goal and can express group behavior. The validity of the system is verified through simulation. Also in this paper, we have observed the agents emergent behavior during simulation.This paper was supported by WonKwang University in 2004.     

Adaptive anti-spam filtering for agglutinative languages: a special case for Turkish

We propose anti-spam filtering methods for agglutinative languages in general and for Turkish in particular. The methods are dynamic and are based on Artificial Neural Networks (ANN) and Bayesian Networks. The developed algorithms are user-specific and adapt themselves with the characteristics of the incoming e-mails. The algorithms have two main components. The first one deals with the morphology of the words and the second one classifies the e-mails by using the roots of the words extracted by the morphological analysis. Two ANN structures, single layer perceptron and multi-layer perceptron, are considered and the inputs to the networks are determined using binary model and probabilistic model. Similarly, for Bayesian classification, three different approaches are employed: binary model, probabilistic model, and advanced probabilistic model. In the experiments, a total of 750 e-mails (410 spam and 340 normal) were used and a success rate of about 90% was achieved.     

A generic fuzzy aggregation operator: rules extraction from and insertion into artificial neural networks

Multilayered feedforward artificial neural networks (ANNs) are black boxes. Several methods have been published to extract a fuzzy system from a network, where the input–output mapping of the fuzzy system is equivalent to the mapping of the ANN. These methods are generalized by means of a new fuzzy aggregation operator. It is defined by using the activation function of a network. This fact lets to choose among several standard aggregation operators. A method to extract fuzzy rules from ANNs is presented by using this new operator. The insertion of fuzzy knowledge with linguistic hedges into an ANN is also defined thanks to this operator.     

Artificial Neural Networks Manipulation Server: Research on the Integration of Databases and Artificial Neural Networks

This paper proposes a new whole and distributed integration approach between Artificial Neural Networks (ANNs) and Databases (DBs) taking into account the different stages of the former’s lifecycle (training, test and running). The integration architecture which has been developed consists of an ANN Manipulation Server (AMS) based on a client-server approach, which improves the ANNs’ manipulation and experimentation capabilities considerably, and also those of their training and test sets, together with their modular reuse among possibly remote applications. Moreover, the chances of integrating ANNs and DBs are analysed, proposing a new level of integration which improves the integration features considerably. This level has not been contemplated yet at full reach in any of the commercial or experimental tools analysed up to the present date. Finally, the application of the integration architecture which has been developed to the specific domain of Environmental Impact Assessments (EIAs) is studied. Thus, the versatility and efficacy of that architecture for developing ANNs is tested. The enormous complexity of the functioning of the patterns which rule the environment’s behaviour, and the great number of variables involved, make it the ideal domain for experimenting on the application of ANNs together with DBs.     

A self-organizing neural network using ideas from the immune system to solve the traveling salesman problem

Most combinatorial optimization problems belong to the NP-complete or NP-hard classes, which means that they may require an infeasible processing time to be solved by an exhaustive search method. Thus, less expensive heuristics in respect to the processing time are commonly used. These heuristics can obtain satisfactory solutions in short running times, but there is no guarantee that the optimal solution will be found. Artificial Neural Networks (ANNs) have been widely studied to solve combinatorial problems, presenting encouraging results. This paper proposes some modifications on RABNET-TSP, an immune-inspired self-organizing neural network, for the solution of the Traveling Salesman Problem (TSP). The modified algorithm is compared with other neural methods from the literature and the results obtained suggest that the proposed method is competitive in relation to the other ones, outperforming them in many cases with regards to the quality (cost) of the solutions found, though demanding a greater time for convergence in many cases.     

Application and development of biologically plausible neural networks in a multiagent artificial life system

The present article introduces the system BioAnt, which is a computational simulation of a small colony of ants (up to 99 members) in which every ant relies on a biologically more plausible artificial neural networks as control mechanism for guidance. The environment, in which the ants are placed, is three-dimensional, consisting of the anthill, sugar, water, earth elevations, walls and predators. The ants’ foraging behavior was successfully implemented as well as some basic defense mechanisms. Typical sensors and actuators of ants were modeled and the efficiency of the connectionist approach has been validated by the comparison with a simple symbolical approach. Apart from several surprising results on technical details, which are reported, the present approach clearly demonstrates the feasibility of such an implementation with connectionist and biologically more plausible principles, offering promising perspectives as a basis for further artificial life systems.     

Artificial neural networks as speech recognisers for dysarthric speech: Identifying the best-performing set of MFCC parameters and studying a speaker-independent approach

Dysarthria is a neurological impairment of controlling the motor speech articulators that compromises the speech signal. Automatic Speech Recognition (ASR) can be very helpful for speakers with dysarthria because the disabled persons are often physically incapacitated. Mel-Frequency Cepstral Coefficients (MFCCs) have been proven to be an appropriate representation of dysarthric speech, but the question of which MFCC-based feature set represents dysarthric acoustic features most effectively has not been answered. Moreover, most of the current dysarthric speech recognisers are either speaker-dependent (SD) or speaker-adaptive (SA), and they perform poorly in terms of generalisability as a speaker-independent (SI) model. First, by comparing the results of 28 dysarthric SD speech recognisers, this study identifies the best-performing set of MFCC parameters, which can represent dysarthric acoustic features to be used in Artificial Neural Network (ANN)-based ASR. Next, this paper studies the application of ANNs as a fixed-length isolated-word SI ASR for individuals who suffer from dysarthria. The results show that the speech recognisers trained by the conventional 12 coefficients MFCC features without the use of delta and acceleration features provided the best accuracy, and the proposed SI ASR recognised the speech of the unforeseen dysarthric evaluation subjects with word recognition rate of 68.38%.     

The modified fuzzy art and a two-stage clustering approach to cell design

This study presents a new pattern recognition neural network for clustering problems, and illustrates its use for machine cell design in group technology. The proposed algorithm involves modifications of the learning procedure and resonance test of the Fuzzy ART neural network. These modifications enable the neural network to process integer values rather than binary valued inputs or the values in the interval [0, 1], and improve the clustering performance of the neural network. A two-stage clustering approach is also developed in order to obtain an informative and intelligent decision for the problem of designing a machine cell. At the first stage, we identify the part families with very similar parts (i.e., high similarity exists in their processing requirements), and the resultant part families are input to the second stage, which forms the groups of machines. Experimental studies show that the proposed approach leads to better results in comparison with those produced by the Fuzzy ART and other similar neural network classifiers.     

Generalized neural network and wavelet transform based approach for fault location estimation of a transmission line

To maintain the efficient and reliable operation of power systems, it is extremely important that the transmission line faults need to be detected and located in a reliable and accurate manner. A number of mathematical and intelligent techniques are available in the literature for estimating the fault location. However, the results are not satisfactory due to the wide variation in operating conditions such as system loading level, fault inception instance, fault resistance and dc offset and harmonics contents in the transient signal of the faulted transmission line. Keeping in view of aforesaid, a new approach based on generalized neural network (GNN) with wavelet transform is presented for fault location estimation. Wavelet transform is used to extract the features of faulty current signals in terms of standard deviation. Obtained features are used as an input to the GNN model for estimating the location of fault in a given transmission systems. Results obtained from GNN model are compared with ANN and well established mathematical models and found more accurate.     

BP神经网络在甘油水溶液粘度预测中的应用

二维数据表广泛应用于科学与工程计算,当出现数据缺失时,由于数据间存在的非线性关系,采用传统方法在两列数据中插值将产生较大的误差.结合甘油水溶液粘度的预测,提出使用人工神经网络的插值方法,对神经网络模型、参数以及训练样本集的选择进行了实验与优化.实验表明,利用BP神经网络预测25℃甘油水溶液粘度时,网络收敛速度快,预测精度高,优于传统的最邻近插值和双线性插值,能够满足一般科学与工程计算的需要.提出的插值预测方法对类似条件的二维数据表具有普遍指导意义.     

数据挖掘技术在运动目标轨迹预测中的应用

该文提出了一种利用数据挖掘技术对运动目标的轨迹进行预测的方法,给出了具体的预测算法和实例。并在传统的人工神经网络和遗传算法的基础上,提出了一种新的方法:混配。采用混配的方法,克服了遗传算法中所存在的种群内过早收敛的缺点,极大地提高了预测算法的准确度。     

A comparison between functional networks and artificial neural networks for the prediction of fishing catches

In recent years, functional networks have emerged as an extension of artificial neural networks (ANNs). In this article, we apply both network techniques to predict the catches of the Prionace Glauca (a class of shark) and the Katsowonus Pelamis (a variety of tuna, more commonly known as the Skipjack). We have developed an application that will help reduce the search time for good fishing zones and thereby increase the fleets competitivity. Our results show that, thanks to their superior learning and generalisation capacities, functional networks are more efficient than ANNs. Our data proceeds from remote sensors. Their spectral signatures allow us to calculate products that are useful for ecological modelling. After an initial phase of digital image processing, we created a database that provides all the necessary patterns to train both network types.     

一种适用于模式识别的新型神经网络

提出了一种适用于模式识别的新型神经网络模型——局部有监督特征映射网络,描述了该网络的拓扑结构和学习算法,研究了网络的基本性能,最后将其应用到了质量控制图的模式识别中。理论研究和仿真实验表明,该网络结构简单、算法简洁,收敛速度快、识别精度高,适用于需要大样本训练、随机干扰严重的复杂模式的分类与识别。     

The application of an artificial immune system-based back-propagation neural network with feature selection to an RFID positioning system

This study uses the Received Signal Strength Indication (RSSI) values of RFID to predict the position of picking staff for warehouse management. A proposed feature selection-based back-propagation (BP) neural network that uses an artificial immune system (AIS) (FSBP-AIS) to determine the connecting weights of a neural network learns the relationship between the RSSI values and the position of the picking staff. In addition, the proposed FSBP-AIS is able to determine the representative features, or inputs, during training. Once a picking staff's position is known, this information is used to plan the picking route for picking staff if a new order arrives. The computational results indicate that the proposed FSBP-AIS can provide better predictions than a traditional BP neural network, BP neural network with stepwise regression to determine the important inputs, and regression method.     

多元回归分析及其在辅助决策中的应用

研究了人工神经网络,多元回归分析以及如何应用改进的BP算法求解多元回归模型。给出了在软件产业中进行辅助决策的应用实例,建立了软件销售额与软件产业中博士,硕士和学士数量之间的回归模型,提出了多元回归与一元回归分析相结合的预测方法,并将预测结果与一元回归分析所得的结果进行了对比分析。