Course Description and Goals

Course Description

This course provides a comprehensive introduction to deep learning, progressing from linear regression to state-of-the-art architectures like transformers. Students will implement fully connected neural networks from scratch to build a solid foundation and explore convolutional neural networks (CNNs), transformers, and generative models. Hands-on experience with modern tools like PyTorch will be emphasized, enabling students to design, train, and evaluate deep learning models for tasks in computer vision, natural language processing, and beyond.

Course Goals

• Understand the theoretical foundations of deep learning and implement feedforward neural networks from scratch.

• Gain hands-on experience using PyTorch to design, train, and evaluate deep learning models.

• Apply convolutional neural networks (CNNs), transformers, and diffusion models to real-world tasks.

• Explore generative models like GANs and VAEs and their applications in AI.

• Build and optimize deep learning solutions for domains such as computer vision and natural language processing.