Abstract
For a long time neural networks have been a popular approach for intelligent machines development and knowledge discovery. However, problems still exists in neural networks, such as fixed architecture and excessive training time. One of the solutions to unravel this problem is by using neuro-genetic approach. A neuro-genetic approach is inspired by a theory in neuroscience which state that the evolution of human brain structure is significantly affected by its genome structure. Hence, the structure and performance of a neural network should be based on a gene created for it. Therefore, to overcome these existing neural network problems and with the help of new theory of neuroscience this paper we attempt to propose a neuro-genetic approach by using simple Gene Regulatory Network (GRN) as a more biologically plausible model of neural network.
Firstly, we proposed GRTE, a Gene Regulatory Training Engine to control, evaluate, mutate and train genes. Secondly, ANNN, a distributed and Adaptive Nested Neural Network that will be constructed based on the genes from GRTE. This paper focuses on ANNN for Uncorrelated Data. We conducted experiments to evaluate and validate by using the Proben1's Gene Benchmark Datasets. The results of the experiments validate the objective of this work.