111 resultados para Recurrent Neural Networks
em Deakin Research Online - Australia
Resumo:
Learning in neural networks can broadly be divided into two categories, viz., off-line (or batch) learning and online (or incremental) learning. In this paper, a review of a variety of supervised neural networks with online learning capabilities is presented. Specifically, we focus on articles published in main indexed journals in the past 10 years (2003–2013). We examine a number of key neural network architectures, which include feedforward neural networks, recurrent neural networks, fuzzy neural networks, and other related networks. How the online learning methodologies are incorporated into these networks is exemplified, and how they are applied to solving problems in different domains is highlighted. A summary of the review that covers different network architectures and their applications is presented.
Resumo:
Artificial neural networks (ANN) are increasingly used to solve many problems related to pattern recognition and object classification. In this paper, we report on a study using artificial neural networks to classify two kinds of animal fibers: merino and mohair. We have developed two different models, one extracting nine scale parameters with image processing, and the other using an unsupervised artificial neural network to extract features automatically, which are determined in accordance with the complexity of the scale structure and the accuracy of the model. Although the first model can achieve higher accuracy, it requires more effort for image processing and more prior knowledge, since the accuracy of the ANN largely depends on the parameters selected. The second model is more robust than the first, since only raw images are used. Because only ordinary optical images taken with a microscope are employed, we can use the approach for many textile applications without expensive equipment such as scanning electron microscopy.
Resumo:
In this paper, a visual feedback control approach based on neural networks is presented for a robot with a camera installed on its end-effector to trace an object in an unknown environment. First, the one-to-one mapping relations between the image feature domain of the object to the joint angle domain of the robot are derived. Second, a method is proposed to generate a desired trajectory of the robot by measuring the image feature parameters of the object. Third, a multilayer neural network is used for off-line learning of the mapping relations so as to produce on-line the reference inputs for the robot. Fourth, a learning controller based on a multilayer neural network is designed for realizing the visual feedback control of the robot. Last, the effectiveness of the present approach is verified by tracing a curved line using a 6-degrees-of-freedom robot with a CCD camera installed on its end-effector. The present approach does not necessitate the tedious calibration of the CCD camera and the complicated coordinate transformations.
Resumo:
Selection of the topology of a neural network and correct parameters for the learning algorithm is a tedious task for designing an optimal artificial neural network, which is smaller, faster and with a better generalization performance. In this paper we introduce a recently developed cutting angle method (a deterministic technique) for global optimization of connection weights. Neural networks are initially trained using the cutting angle method and later the learning is fine-tuned (meta-learning) using conventional gradient descent or other optimization techniques. Experiments were carried out on three time series benchmarks and a comparison was done using evolutionary neural networks. Our preliminary experimentation results show that the proposed deterministic approach could provide near optimal results much faster than the evolutionary approach.
Resumo:
Although the development of geographic information system (GIS) technology and digital data manipulation techniques has enabled practitioners in the geographical and geophysical sciences to make more efficient use of resource information, many of the methods used in forming spatial prediction models are still inherently based on traditional techniques of map stacking in which layers of data are combined under the guidance of a theoretical domain model. This paper describes a data-driven approach by which Artificial Neural Networks (ANNs) can be trained to represent a function characterising the probability that an instance of a discrete event, such as the presence of a mineral deposit or the sighting of an endangered animal species, will occur over some grid element of the spatial area under consideration. A case study describes the application of the technique to the task of mineral prospectivity mapping in the Castlemaine region of Victoria using a range of geological, geophysical and geochemical input variables. Comparison of the maps produced using neural networks with maps produced using a density estimation-based technique demonstrates that the maps can reliably be interpreted as representing probabilities. However, while the neural network model and the density estimation-based model yield similar results under an appropriate choice of values for the respective parameters, the neural network approach has several advantages, especially in high dimensional input spaces.
Resumo:
Artificial neural network (NN) is an alternative way (to conventional physical or chemical based modeling technique) to solve complex ill-defined problems. Neural networks trained from historical data are able to handle nonlinear problems and to find the relationship between input data and output data when there is no obvious one between them. Neural Networks has been successfully used in control, robotic, pattern recognition, forecasting areas. This paper presents an application of neural networks in finding some key factors eg. heat loss factor in power station modeling process. In the conventional modeling of power station, these factors such as heat loss are normally determined by experience or “rule of thumb”. To get an accurate estimation of these factors special experiment needs to be carried out and is a very time consuming process. In this paper the neural networks (technique) is used to assist this difficult conventional modeling process. The historical data from a real running brown coal power station in Victoria has been used to train the neural network model and the outcomes of the trained NN model will be used to determine the factors in the conventional energy modeling of the power stations that is under the development as a part of an on-going ARC Linkage project aiming to detail modeling the internal energy flows in the power station.
Resumo:
The aim of this work is to improve the quality of castings by minimizing defects and scrap through the analysis of the data generated by High Pressure Die Casting (HPDC) Machines using computational intelligence techniques. Casting is a complex process that is affected by the interdependence of die casting process parameters on each other such that changes in one parameter results in changes in other parameters. Computational intelligence techniques have the potential to model accurately this complex relationship. The project has the potential to generate optimal configurations for HPDC Machines and explain the relationships between die casting process parameters.
Resumo:
The eigenvector associated with the smallest eigenvalue of the autocorrelation matrix of input signals is called minor component. Minor component analysis (MCA) is a statistical approach for extracting minor component from input signals and has been applied in many fields of signal processing and data analysis. In this letter, we propose a neural networks learning algorithm for estimating adaptively minor component from input signals. Dynamics of the proposed algorithm are analyzed via a deterministic discrete time (DDT) method. Some sufficient conditions are obtained to guarantee convergence of the proposed algorithm.
Resumo:
This thesis provides a unified and comprehensive treatment of the fuzzy neural networks as the intelligent controllers. This work has been motivated by a need to develop the solid control methodologies capable of coping with the complexity, the nonlinearity, the interactions, and the time variance of the processes under control. In addition, the dynamic behavior of such processes is strongly influenced by the disturbances and the noise, and such processes are characterized by a large degree of uncertainty. Therefore, it is important to integrate an intelligent component to increase the control system ability to extract the functional relationships from the process and to change such relationships to improve the control precision, that is, to display the learning and the reasoning abilities. The objective of this thesis was to develop a self-organizing learning controller for above processes by using a combination of the fuzzy logic and the neural networks. An on-line, direct fuzzy neural controller using the process input-output measurement data and the reference model with both structural and parameter tuning has been developed to fulfill the above objective. A number of practical issues were considered. This includes the dynamic construction of the controller in order to alleviate the bias/variance dilemma, the universal approximation property, and the requirements of the locality and the linearity in the parameters. Several important issues in the intelligent control were also considered such as the overall control scheme, the requirement of the persistency of excitation and the bounded learning rates of the controller for the overall closed loop stability. Other important issues considered in this thesis include the dependence of the generalization ability and the optimization methods on the data distribution, and the requirements for the on-line learning and the feedback structure of the controller. Fuzzy inference specific issues such as the influence of the choice of the defuzzification method, T-norm operator and the membership function on the overall performance of the controller were also discussed. In addition, the e-completeness requirement and the use of the fuzzy similarity measure were also investigated. Main emphasis of the thesis has been on the applications to the real-world problems such as the industrial process control. The applicability of the proposed method has been demonstrated through the empirical studies on several real-world control problems of industrial complexity. This includes the temperature and the number-average molecular weight control in the continuous stirred tank polymerization reactor, and the torsional vibration, the eccentricity, the hardness and the thickness control in the cold rolling mills. Compared to the traditional linear controllers and the dynamically constructed neural network, the proposed fuzzy neural controller shows the highest promise as an effective approach to such nonlinear multi-variable control problems with the strong influence of the disturbances and the noise on the dynamic process behavior. In addition, the applicability of the proposed method beyond the strictly control area has also been investigated, in particular to the data mining and the knowledge elicitation. When compared to the decision tree method and the pruned neural network method for the data mining, the proposed fuzzy neural network is able to achieve a comparable accuracy with a more compact set of rules. In addition, the performance of the proposed fuzzy neural network is much better for the classes with the low occurrences in the data set compared to the decision tree method. Thus, the proposed fuzzy neural network may be very useful in situations where the important information is contained in a small fraction of the available data.