Lotta Rantala

Background

About Lotta Rantala

Hello, I am Lotta! I have recently completed my Master of Science in Technology in Computer Science and Engineering at University of Oulu. My studies were mainly focused on artificial intelligence, with the Module of Option dedicated to AI. Throughout my studies, I gained a comprehensive understanding of machine learning, data-driven modeling, and optimization techniques, while also developing strong skills in software development, programming and applied research methods. In my Master's thesis, I implemented and evaluated deep neural network models for digital pre-distortion of radio frequency power amplifiers. The model architectures consisted of multiple concepts from literature combined into larger models. I performed a hyperparameter search for improved model performance, and an ablation study to evaluate how much each model component contributes to the overall model performance. The results showed that the neural network models outperform traditional polynomial-based models in the linearization of power amplifiers, and approach the performance of ideal pre-distortion.