In this paper we propose a constructive algorithm with adaptive sigmoidal function for designing single hidden layer feedforward neural network (CAASF). The proposed algorithm emphasizes on architectural adaptation an...
详细信息
ISBN:
(纸本)9783037853122
In this paper we propose a constructive algorithm with adaptive sigmoidal function for designing single hidden layer feedforward neural network (CAASF). The proposed algorithm emphasizes on architectural adaptation and functional adaptation during training. This algorithm is a constructive approach to building single hidden layer neural networks dynamically. The activation functions used at non-linear hidden nodes are belonging to the well-defined sigmoidal class and adapted during training. The algorithm determines not only optimum number of hidden nodes, as also optimum sigmoidal function for the non-linear nodes. One simple variant derived from CAASF is where the sigmoidal function used at the hidden nodes is fixed. Both the variants are compared to each other on five regression functions. Simulation results reveal that adaptive sigmoidal function presents several advantages over traditional fixed sigmoid function, resulting in increased flexibility, smoother learning, better convergence and better generalization performance.
The objective of this paper is the application of an adaptive constructive one-hidden-layer feedforward neural networks (OHL-FNNs) to image compression. Comparisons with fixed structure neural networks are performed t...
详细信息
The objective of this paper is the application of an adaptive constructive one-hidden-layer feedforward neural networks (OHL-FNNs) to image compression. Comparisons with fixed structure neural networks are performed to demonstrate and illustrate the training and the generalization capabilities of the proposed adaptive constructive networks. The influence of quantization effects as well as comparison with the baseline JPEG scheme are also investigated. It has been demonstrated through several experiments that very promising results are obtained as compared to presently available techniques in the literature.
Networked Control Systems (NCS) are used for remote control of distributed or non- co-located systems where the control loop is closed via a communication link. Remote access to industrial robotic systems is one of th...
详细信息
Networked Control Systems (NCS) are used for remote control of distributed or non- co-located systems where the control loop is closed via a communication link. Remote access to industrial robotic systems is one of the application fields where robustness and reliability of the closed loop plays a significant role. Caused by the communication chain in the control loop, there are challenging constraints that can affect the stability and performance of a closed loop. One can consider a large number of difficulties in this type of control systems, for instance unknown delay and packet drop-out. There are already a large number of methods and approaches to handle issues in the NCS and because of increasing interest of the industry, many are still being developed to improve the features of the closed loops over communication networks. This paper summarizes the existing theory of the networked control systems under communication constraints and presents an H∞ synthesis for a simple plant. Finally the results are illustrated, discussed and validated using real measurements from a robotic system.
A study of the function approximation capabilities of single hidden layer neural networks strongly motivates the investigation of constructive learning techniques as a means of realizing established error bounds. Lear...
详细信息
A study of the function approximation capabilities of single hidden layer neural networks strongly motivates the investigation of constructive learning techniques as a means of realizing established error bounds. Learning characteristics employed by constructive algorithms provide ideas for development of new algorithms applicable to the function approximation problem. In addition, constructive techniques offer efficient methods for network construction and weight determination. The development of a novel neural network algorithm, the constructive Locally Fit Sigmoids (CLFS) function approximation algorithm, is presented in detail. Basis functions of global extent (piecewise linear sigmoidal functions) are locally fit to the target function, resulting in a pool of candidate hidden layer nodes from which a function approximation is obtained. This algorithm provides a methodology of selecting nodes in a meaningful way from the infinite set of possibilities and synthesizes an n node single hidden layer network with empirical and analytical results that strongly indicate an O(1/n) mean squared training error bound under certain assumptions. The algorithm operates in polynomial time in the number of network nodes and the input dimension. Empirical results demonstrate its effectiveness on several multidimensional function approximate problems relative to contemporary constructive and nonconstructive algorithms.
constructive algorithms have proved to be powerful methods for training feedforward neural networks. An important property of these algorithms is generalization. A series of empirical studies were performed to examine...
详细信息
constructive algorithms have proved to be powerful methods for training feedforward neural networks. An important property of these algorithms is generalization. A series of empirical studies were performed to examine the effect of regularization on generalization in constructive cascade algorithms. It was found that the combination of early stopping and regularization resulted in better generalization than the use of early stopping alone. A cubic penalty term that greatly penalizes large weights was shown to be beneficial for generalization in cascade networks. An adaptive method of setting the regularization magnitude in constructive algorithms was introduced and shown to produce generalization results similar to those obtained with a fixed, user-optimized regularization setting. This adaptive method also resulted in the construction of smaller networks for more complex problems. The acasper algorithm, which incorporates the insights obtained from the empirical studies, was shown to have good generalization and network construction properties. This algorithm was compared to the cascade correlation algorithm on the Proben 1 and additional regression data sets.
This article presents the design and evaluation of transit networks using a route expansion heuristic and agent-based travel demand simulation. The route expansion mechanism is a type of constructive heuristic algorit...
详细信息
This article presents the design and evaluation of transit networks using a route expansion heuristic and agent-based travel demand simulation. The route expansion mechanism is a type of constructive heuristic algorithm that derives new transit routes by inserting neighbouring nodes into existing routes with the aim of improving the demand coverage. The resulting networks are evaluated with an agent-based travel demand simulation model. The use of agent-based modelling is a departure from the existing route expansion literature and indeed the broader transit network design discipline in which the four step model has been extensively used. The procedure is tested on a bus rapid transit network in the City of Cape Town in South Africa.
The design phase of B-spline neural networks is a highly computationally complex task. Existent heuristics have been found to be highly dependent on the initial conditions employed. Increasing interest in biologically...
详细信息
The design phase of B-spline neural networks is a highly computationally complex task. Existent heuristics have been found to be highly dependent on the initial conditions employed. Increasing interest in biologically inspired learning algorithms for control techniques such as Artificial Neural Networks and Fuzzy Systems is in progress. In this paper, the Bacterial Programming approach is presented, which is based on the replication of the microbial evolution phenomenon. This technique produces an efficient topology search, obtaining additionally more consistent solutions.
Previous research has demonstrated that constructive algorithms are powerful methods for training feedforward neural networks. The CasPer algorithm is a constructive neural network algorithm that generates networks fr...
详细信息
ISBN:
(纸本)9781467314886
Previous research has demonstrated that constructive algorithms are powerful methods for training feedforward neural networks. The CasPer algorithm is a constructive neural network algorithm that generates networks from a simple architecture and then expands it. The A_CasPer algorithm is a modified version of the CasPer algorithm which uses a candidate pool instead of a single neuron being trained. This research adds an extension to the A_CasPer algorithm in terms of the network architecture - the Layered_CasPer algorithm. The hidden neurons form as layers in the new version of the network structure which results in less computational cost being required. Beyond the network structure, other aspects of Layered_CasPer are the same as A_CasPer. The Layered_CasPer algorithm extension is benchmarked on a number of classification problems and compared to other constructive algorithms, which are CasCor, CasPer, A_CasPer, and AT_CasPer. It is shown that Layered_CasPer has a better performance on the datasets which have a large number of inputs for classification tasks. The Layered_CasPer algorithm has an advantage over other cascade style constructive algorithms in being more similar in topology to the familiar layered structure of traditional feedforward neural networks.
暂无评论