This lecture provides a comprehensive introduction to contemporary Deep Learning methods, with a specific emphasis on their practical application. Concurrently, it serves as a primer for the widely-used PyTorch Deep Learning framework, assuming only a basic familiarity with Python. The course encompasses a wide range of prevalent machine learning tasks across various data types, including tabular, image, text, audio, and graph data. Throughout the course, we delve into the most crucial and up-to-date model architectures within these domains. This encompasses convolutional neural networks, recurrent neural networks, and transformer models. The lecture is complemented by hands-on exercise sessions, where students will gain practical proficiency with PyTorch. Simultaneously, they will acquire practical insights to effectively apply contemporary deep learning methods within their specific fields of interest.