Deep Learning Fundamentals (BTBS325)
This course introduces the principles and practical applications of neural networks and deep learning. Students will explore key structures, including perceptrons, multi-layer perceptrons (MLPs), and the differences between shallow and deep networks, focusing on design, operation, and learning methods. Essential training techniques such as backpropagation, regularization, and dropout will be covered. Advanced architectures include Convolutional Neural Networks (CNNs) for computer vision and Recurrent Neural Networks (RNNs), including GRUs and LSTMs, for sequential data processing. Practical exercises provide hands-on experience in building, training, and applying deep learning models. Theoretical concepts are reinforced with examples, coding tasks, and problem-solving activities. By the end of the course, students will have the skills to design, build, and apply deep learning solutions to real-world problems.