Structural-Parametric Synthesis of the Direct Distribution Neural Networks with Sigmoid Piecewise-Type Neurons

UDC 681.327.12(045) DOI:10.18372/1990-5548.58.13508

  1. Zgurovsky M. Z., Chumachenko O. I., Gorbatiuk V. S. Structural-Parametric Synthesis of the Direct Distribution Neural Networks with Sigmoid Piecewise-Type Neurons // Electronics and Control Systems, N 4(58) – Kyiv: NAU, 2018. – pp. 42–47.

The method of structural and parametric synthesis of feedforward neural networks is considered, which includes Sigmoid Piecewise neurons, used in the process of a predictive model construction. The article describes the principles of a new developed Sigmoid Piecewise neuron constructing. It is proposed the method of structural and parametric synthesis with a single layer of Sigmoid Piecewise neurons.The training algorithm of proposed neural networks is developed. The results of the effectiveness research of Sigmoid Piecewise neurons on real samples are presented.

Index Terms—Feedforward neural networks; time series; sigmoid piecewise; training algorithm.

References: 8 name.