Search results

This paper aims to compare stochastic gradient method used for neural network training with global optimizer without use of gradient information, in particular differential evolution.

This contribute shows the application of heuristic optimization algorithms to the training phase of artificial neural network whose aim is to predict renewable power production as function of environmental variables such as solar irradiance and temperature. The training problem is cast as the minimization of a cost function whose degrees of freedom are the parameters of the neural network. A differential evolution algorithm is substituted to the more usual gradient-based minimization procedure, and the comparison of their performances is presented.

The two procedures based on stochastic gradient and differential evolution reach the same results being the gradient based moderately quicker in convergence but with a lower value of reliability, as a significant number of runs do not reach convergence.

The approach has been applied to two forecasting problems and, even if results are encouraging, the need for extend the approach to other problems is needed.

The new approach could open the training of neural network to more stable and general methods, exploiting the potentialities of parallel computing.

To the best of the authors’ knowledge, the research presented is fully original for the part regarding the neural network training with differential evolution.