A constrained approximate dynamic programming (ADP) approach is presented for designing adaptive neural network (NN) controllers with closed-loop stability and performance guarante...
This paper introduces a learning method for two-layer feedforward neural networks based on sensitivity analysis, which uses a linear training algorithm for each of the two layers....
One of the major difficulties when applying Multiobjective Evolutionary Algorithms (MOEA) to real world problems is the large number of objective function evaluations. Approximate...
A. K. M. Khaled Ahsan Talukder, Michael Kirley, Ra...
Speciation is an important concept in evolutionary computation. It refers to an enhancements of evolutionary algorithms to generate a set of diverse solutions. The concept is stud...
— In connectionist learning, one relevant problem is “catastrophic forgetting” that may occur when a network, trained with a large set of patterns, has to learn new input pat...
Dario Albesano, Roberto Gemello, Pietro Laface, Fr...