A typical machine learning application often involves a challenging procedure composed of data preprocessing, feature extraction, architecture selection, and hyperparameter tuning. Automated machine learning, or AutoML, aims to simplify this complex process. In this project, I designed an AutoML algorithm using a cascaded architecture comprised of a Nelder-Mead method and a genetic algorithm. The resulting algorithm is able to learn both the architecture and the parameters of a neural network fully autonomously. On the MNIST dataset, the optimized model achieved 89% accuracy.
Repository: https://github.com/Yahnnosh/Automated-Machine-Learning-Using-Genetic-Algorithm/tree/dev
Portfolio 