Biological models of artificial networks

The last several years have seen a dramatic increase in the number of neurobiologists building or using computer-based models as a regular part of their efforts to understand how different neural systems function. Computational neuroscience focuses on how the nervous system computes, and several models have been proposed that describe neural behavior at the cellular as well as a network level [11]. Artificial neural networks (ANN), originally inspired by their biological counterpart, are far from being analogous to the biological neural networks. After simple models proved useful, relatively little work has been done to make artificial neural networks more like biological systems. Even as strictly computational devices, current ANN systems have problems, such as local minima, network configuration, and preparation of input data. In this work, Biological network configurations of species like aplysia will be studied to understand the learning processes and to look for ways to incorporate the ideas into artificial networks.