Model Development

Catalog description

In this course on applied machine learning, students will master the process of selecting, training, and evaluating algorithms using real-world datasets and cutting-edge machine learning techniques. Through hands-on exercises and projects, participants will gain practical experience in data preprocessing, feature engineering, and model optimization for both supervised and unsupervised learning scenarios, as well as reinforcement learning fundamentals. The curriculum includes the use of foundational models and transfer learning, enabling students to apply common models to new use cases. Performance validation using a variety of metrics will be emphasized, ensuring students can effectively measure and optimize model performance for different applications. The course also addresses the computing infrastructure required for model development and deployment, providing insights into scalable solutions using cloud-based platforms.