Evolvable Neural Networks Research Articles

Evolvable Neural Networks for Time Series Prediction with Adaptive Learning Interval

This paper presents adaptive learning data of evolvable neural networks (ENNs) for time series prediction of nonlinear dynamic systems. ENNs are a special class of neural networks that adopt the concept of biological evolution as a mechanism of adaptation or learning. ENNs can adapt to an environment as well as changes in the enviromuent. ENNs used in this paper are L-system and DNA coding based ENNs. The ENNs adopt the evolution of simultaneous network architecture and weights using indirect encoding. In general just previous data are used for training the predictor that predicts future data. However the characteristics of data and appropriate size of learning data are usually unknown. Therefore we propose adaptive change of learning data size to predict the future data effectively. In order to verify the effectiveness of our scheme, we apply it to chaotic time series predictions of Mackey-Glass data.

Evolvable Neural Networks Based on Developmental Models for Mobile Robot Navigation

This paper presents evolvable neural networks based on a developmental model for navigation control of autonomous mobile robots in dynamic operating environments. Bio-inspired mechanisms have been applied to autonomous design of artificial neural networks for solving practical problems. The proposed neural network architecture is grown from an initial developmental model by a set of production rules of the L-system that are represented by the DNA coding. The L-system is based on parallel rewriting mechanism motivated by the growth models of plants. DNA coding gives an effective method of expressing general production rules. Experiments show that the evolvable neural network designed by the production rules of the L-system develops into a controller for mobile robot navigation to avoid collisions with the obstacles.

Creatures: an exercise in creation

Why do we create neural networks that have no chemistry? Why simulate genetics without a digestive system? There is no such thing as half an organism, yet most attempts to generate intelligent or life-like agents are based essentially on a single mechanism. Granted, a few people are working on evolvable neural networks, but the genetics is seen as a means to an end, rather than a part of an integrated, heterogeneous system. Neural networks themselves are generally homogeneous entities, too-one kind of neuron, interconnected in one or at most a few different ways and performing a single task. Yet, we know that our brains are not like that at all: they are divided into regions that perform many different tasks and contain populations of very different cells. What is more, artificial neural networks generally employ only direct synaptic connections for their signal paths, despite our awareness that real brains are swimming in neurotransmitters that have diffuse and plural functions. Taking a holistic approach and attempting to create such a "whole" organism might sound like a brave or even foolhardy task. However, in this article, I explore the possibilities and see what could be done.