Related Experiment Video
Updated: Jul 23, 2026

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
Published on: March 2, 2015
A real-coded genetic algorithm for training recurrent neural networks
A Blanco1, M Delgado, M C Pegalajar
1Department of Computer Science and Artificial Intelligence, ETSI Informática, University of Granada, Spain.
Abstract:
The use of Recurrent Neural Networks is not as extensive as Feedforward Neural Networks. Training algorithms for Recurrent Neural Networks, based on the error gradient, are very unstable in their search for a minimum and require much computational time when the number of neurons is high. The problems surrounding the application of these methods have driven us to develop new training tools. In this paper, we present a Real-Coded Genetic Algorithm that uses the appropriate operators for this encoding type to train Recurrent Neural Networks. We describe the algorithm and we also experimentally compare our Genetic Algorithm with the Real-Time Recurrent Learning algorithm to perform the fuzzy grammatical inference.
Related Concept Videos
The Central Dogma
Neural Regulation
The Central Dogma
RNA is the Missing Link Between DNA and Proteins
In the early 1900s, scientists discovered that DNA stores all the information needed for cellular functions and that proteins perform most of these functions. However, the mechanisms of converting genetic information into functional proteins remained unknown for many years. Initially, it was believed that a single gene is...
Neural Circuits
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
Sequence Networks of Rotating Machines
Zero-sequence current induces a voltage drop across the generator's neutral impedance and other...
Gradient Vectors and Their Applications

