Hyperparameter Optimization of Two-Hidden-Layer Neural Networks for Power Amplifiers Behavioral Modeling Using Genetic Algorithms

Siqi Wang (1) , Morgan Roger (1, 2) , Julien Sarrazin (3, 1) , Caroline Lelandais-Perrault (1, 2)

1 GeePs - Laboratoire Génie électrique et électronique de Paris
2 CentraleSupélec
3 L2E - Laboratoire d'Electronique et Electromagnétisme

Neural networks (NN) are efficient techniques for behavioral modeling of power amplifiers (PA). This paper proposes a genetic algorithm to determine the optimal hyperparam-eters of the NN model for a PA. Different activation functions are compared. The necessary number of training epochs is also studied to get an optimal solution with a significantly reduced computational complexity. Experimental measurements on a PA with different signals validate the NN models determined by the proposed method.

Keywords: Index Terms-Behavioral modeling; genetic algorithm; neural networks; nonlinear distortion; power amplifiers

Domains: Engineering Sciences [physics]; Signal and Image processing; Engineering Sciences [physics]; Micro and nanotechnologies/Microelectronics; Engineering Sciences [physics]; Electronics

Siqi Wang, Morgan Roger, Julien Sarrazin, Caroline Lelandais-Perrault. Hyperparameter Optimization of Two-Hidden-Layer Neural Networks for Power Amplifiers Behavioral Modeling Using Genetic Algorithms. IEEE Microwave and Wireless Components Letters, 2019, 29 (12), pp.802-805. ⟨10.1109/LMWC.2019.2950801⟩. ⟨hal-02397943⟩