Convergent design of a piecewise linear neural network
نویسندگان
چکیده
A piecewise linear neural network (PLNN) is discussed which maps N-dimensional input vectors into Mdimensional output vectors. A convergent algorithm for designing the PLNN from training data is described. The design algorithm is based on a variation of backtracking algorithm known as the ‘branch and bound’ method. The performance of the PLNN is compared with that of a multilayer perceptron (MLP) of equivalent size. The results show that the PLNN is capable of performing as well as an equivalent MLP.
منابع مشابه
Convergent design of piecewise linear neural networks
Piecewise linear networks (PLNs) are attractive because they can be trained quickly and provide good performance in many nonlinear approximation problems. Most existing design algorithms for piecewise linear networks are not convergent, non-optimal, or are not designed to handle noisy data. In this paper, four algorithms are presented which attack this problem. They are: (1) a convergent design...
متن کاملThe relationship between Neural Networks and DEA-R (Case Study: Companies Stock Exchange)
Evaluate the performance of companies on the Stock Exchange using non-parametric methods is very important. DEA and DEA-R with the strategies for piecewise linear frontier production function and use of available data, assess the stock company. In this study, using a neural network algorithm DEA and DEA-R is suggested to classify the first companies in the stock exchange; Secondly, using the...
متن کاملPiecewise linear system modeling based on a continuous threshold decomposition
The continuous threshold decomposition is a segmentation operator used to split a signal into a set of multilevel components. This decomposition method can be used to represent continuous multivariate piecewise linear (PWL) functions, and therefore can be employed to describe PWL systems deened over a rectangular lattice. The resulting lters are canonical and have a multi-channel structure that...
متن کاملEVALUATION OF CONCRETE COMPRESSIVE STRENGTH USING ARTIFICIAL NEURAL NETWORK AND MULTIPLE LINEAR REGRESSION MODELS
In the present study, two different data-driven models, artificial neural network (ANN) and multiple linear regression (MLR) models, have been developed to predict the 28 days compressive strength of concrete. Seven different parameters namely 3/4 mm sand, 3/8 mm sand, cement content, gravel, maximums size of aggregate, fineness modulus, and water-cement ratio were considered as input variables...
متن کاملA dual neural network for convex quadratic programming subject to linear equality and inequality constraints
A recurrent neural network called the dual neural network is proposed in this Letter for solving the strictly convex quadratic programming problems. Compared to other recurrent neural networks, the proposed dual network with fewer neurons can solve quadratic programming problems subject to equality, inequality, and bound constraints. The dual neural network is shown to be globally exponentially...
متن کامل