ARTIFICIAL NEURAL NETWORK

Artificial Neural Network

Artificial Neural Network

Introduction

An ANN (Artificial Neural Network) is a mathematical model inspired in the biological behavior of neurons and brain structure. This can also be seen as an intelligent system that performs ta- areas differently than they do today's computers. While estasultimas are very fast in processing information, there complex tasks such as pattern recognition and classification, which demand much time and effort even more potential computers ing today, but that the human brain is more able to address them, often without apparent effort (consider the reader as an example the recognition foundation of a familiar face in a crowd of other faces). The brain can be considered a highly complex system. Its basic unit, the neuro- na, is massively distributed connections between them (it is estimated that approximately 10 billion neurons in the cerebral cortex and 60 trillion neuronal connections)[1]

The Data

Floated on the surface of economic life, a set of processes that would hide the sources of funds and try to integrate them into illegal activities and projects, termed "money laundering" and became a multi-dimensional phenomenon. [3]We have formed teams and committees for the criminalization and regulation to deal with, and monitor compliance with the standards of the most important international observers Institute to this issue at the international level, a Financial Action Task Force against Money Laundering (FATF) Financial Action Task Force, and in spite of the growing importance of addressing the scientific and practical for this processes from several corners of the economic, political, security and justice .. However, it has not been addressed from an accounting perspective, despite the fact that these processes article is money being traded among financial institutions, and through transactions in the most international, between a network of clients at a high level of organization, and has made the study in response to the recommendations of both the FATF, and the Committee on the U.S. Congress assigned to study the phenomenon of money laundering, with recommendation that the use of IT Artificial Intelligence in dealing with money laundering offenses, and then the researcher used the Neural Network Technology through the accounting model, can the accountant banking application to rationalize his personal rule for suspected transactions banking, and thus contribute to the solution is a real problem not the application of a modern tool just for the application.[2]

The neural network model used

Mathematical models and their software or hardware implementation, built on the principle of the organization and functioning of biological neural networks - networks of nerve cells of a living organism. This concept emerged in the study of processes in the brain , and when you try to simulate these processes. The first such attempt was the neural network McCulloch and Pitts [1] . Later, after the development of learning algorithms derived model was used for practical purposes: the challenges of forecasting for Pattern Recognition , task management , etc.

ANN is a system of connected and interacting simple processors ( artificial neurons ...