This course provides a comprehensive introduction to deep learning, a subfield of machine learning that uses artificial neural networks to learn complex, hierarchical feature representations from raw data. Deep learning has revolutionized various fields, including computer vision, audio analysis, natural language processing, and decision-making, with applications ranging from speech recognition to autonomous driving. Students will explore the foundational principles, mathematical concepts, and practical implementations of deep learning. Topics include optimization techniques like gradient descent and backpropagation, essential components such as convolutional and pooling layers, and widely used architectures like convolutional and recurrent neural networks. Hands-on programming assignments will familiarize students with deep learning frameworks such as TensorFlow, PyTorch, or Keras and prepare them to build and train neural network models. A final project will allow students to apply their skills to real-world problems of personal interest. By the end of the course, students will be equipped to tackle AI tasks, understand current research, and pursue advanced studies or careers in deep learning, a field that is increasingly essential in both academia and industry.
P: COMP SCI 362 with at least a C grade
Fall Only.