Continuous Function Structured in Multilayer Perceptron for Global Optimization
This is an incremental method for improving optimization processes in machine learning benchmarking.
The authors tackled global optimization benchmarking problems by modifying gradient information in multilayer perceptrons using functional derivatives, showing this creates an MLP-like landscape and improves optimization availability to handle all parameters simultaneously.
The gradient information of multilayer perceptron with a linear neuron is modified with functional derivative for the global minimum search benchmarking problems. From this approach, we show that the landscape of the gradient derived from given continuous function using functional derivative can be the MLP-like form with ax+b neurons. In this extent, the suggested algorithm improves the availability of the optimization process to deal all the parameters in the problem set simultaneously. The functionality of this method could be improved through intentionally designed convex function with Kullack-Liebler divergence applied to cost value as well.