Evolutionary Neural Networks with Mixed-Integer Hybrid Differential Evolution


A novel application to the optimization of neural networks is presented in this paper. Here, the weight and architecture optimization of neural networks can be formulated as a mixed-integer optimization problem. And then a mixed-integer evolutionary algorithm (Mixed-Integer Hybrid Differential Evolution, MIHDE) is used to optimize the neural network… (More)
DOI: 10.4304/jcp.6.8.1591-1596


7 Figures and Tables