Holographic neuro-predictor for fractional Brownian motion (original) (raw)

2003

Abstract

In this paper we discuss our approach to based on holographic techniques implementation of neuro-fuzzy predictor for processes, described by Fractal Brownian Motion (FBM) model. We use the model of the predictor as a Riemann Stieltjes integral over the observed traffic of specific weight function. We discuss two-layered bi-directional optical neural network to find our solution. To find the weight function we use non-linearity in the correlation layer of the neural network. In our experiments we used air-photograph of forest as this kind of images demonstrates self-similarity property and can be described by the FBM model. As a first step we used approximate solution for the weight function, achieved by using binary filtering function in the correlation layer. We demonstrate experimental results and discuss directions of our future investigations.

Vladimir Vedeneev hasn't uploaded this paper.

Let Vladimir know you want this paper to be uploaded.

Ask for this paper to be uploaded.