This course introduces students to deep learning–based approaches for computer vision, focusing on how modern neural networks enable machines to understand and interpret visual data. It covers core visual recognition tasks such as image classification and object detection, along with the learning algorithms and network architectures that power state-of-the-art computer vision systems used in real-world applications like medical imaging, autonomous systems, and intelligent applications. Through a combination of conceptual explanations and hands-on practice, students learn to implement, train, debug, and fine-tune neural networks while gaining insight into practical engineering techniques and recent advances in computer vision research.