Stability of the random neural network model
Neural Computation
Learning in the recurrent random neural network
Neural Computation
G-networks with multiple classes of negative and positive customers
Theoretical Computer Science
An energy function for the random neural network
Neural Processing Letters
A Fuzzy Cognitive Map Based on the Random Neural Model
Proceedings of the 14th International conference on Industrial and engineering applications of artificial intelligence and expert systems: engineering of intelligent systems
Adaptive Random Fuzzy Cognitive Maps
IBERAMIA 2002 Proceedings of the 8th Ibero-American Conference on AI: Advances in Artificial Intelligence
An initiative for a classified bibliography on G-networks
Performance Evaluation
The Multilayer Random Neural Network
Neural Processing Letters
Hi-index | 0.00 |
Gelenbe has modeled neural networks using an analogy with queuing theory. This model (called Random Neural Network) calculates the probability of activation of the neurons in the network. Recently, Fourneau and Gelenbe have proposed an extension of this model, called multiple classes random neural network model. The purpose of this paper is to describe the use of the multiple classes random neural network model to learn patterns having different colors. We propose a learning algorithm for the recognition of color patterns based upon non-linear equations of the multiple classes random neural network model using gradient descent of a quadratic error function. In addition, we propose a progressive retrieval process with adaptive threshold values. The experimental evaluation shows that the learning algorithm provides good results.