Piecewise-Linear Neural Network – Possible Training Algorithms Efficiency Comparison

Training of Perceptron Neural Network Using Piecewise Linear Activation Function

A new Perceptron training algorithm is presented, which employs the piecewise linear activation function and the sum of squared differences error function over the entire training set. The most commonly used activation functions are continuously differentiable such as the logistic sigmoid function, the hyperbolic-tangent and the arctangent. The differentiable activation functions allow gradient...

Enhanced unit training for piecewise linear seperation incremental algorithms

network optimization with piecewise linear convex costs

the problem of finding the minimum cost multi-commodity flow in an undirected and completenetwork is studied when the link costs are piecewise linear and convex. the arc-path model and overflowmodel are presented to formulate the problem. the results suggest that the new overflow model outperformsthe classical arc-path model for this problem. the classical revised simplex, frank and wolf and a ...

Neural Network Training with Second Order Algorithms

Second order algorithms are very efficient for neural network training because of their fast convergence. In traditional Implementations of second order algorithms [Hagan and Menhaj 1994], Jacobian matrix is calculated and stored, which may cause memory limitation problems when training large-sized patterns. In this paper, the proposed computation is introduced to solve the memory limitation pr...

Neural network piecewise linear preprocessing for time-series prediction