Graduate courses in deep learning for engineering applications.
This course introduces foundational and advanced topics in deep learning with a focus towards engineering applications. Students cover core neural network concepts and architectures, including convolutional, graph, and sequence models, before advancing to generative modeling, representation learning, and foundation models. This course combines 24-788 and 24-789 into a single semester-length offering.
This course provides an introduction to deep learning with an emphasis on engineering applications. Students cover the fundamentals of deep neural networks, and learn how inductive biases influence model design. By the end of the mini, students will be able to implement and apply common deep learning architectures to solve tasks across a variety of engineering domains.
This course builds on 24-788 to explore how deep learning methods scale in data, parameters, and capabilities. Topics include transformers, generative modeling, and representation learning. By the end of the mini, students will be able to implement and apply these frameworks to address engineering problems.