CPEN 455 (Deep Learning) is a course I completed at UBC. The course focused on understanding the concepts and techniques underlying the field on deep learning. The final deliverable of the course was modifying the architecture of a generative model to improve its performance and make it additionally a function as a classifier. We explored the mathematics and theory of backpropagation, optimizers, CNNs, transformers, LLMs, VAEs and more. It was taught by Professor Renjie Liao. UBC provides the following description of the course.
This course will focus on implementation and applications of deep learning systems for tasks such object recognition, speech recognition, language processing, and autonomous driving. Specific concepts will include neural networks, deep neural networks, convolutional neural networks (CNNs), and recurrent neural networks (RNNs) as well as improvement and optimization techniques such as back propagation, gradient decent, parameter tuning and regularization. This course will involve extensive hands-on programming assignments. Comfort programming in a high level languages such as Matlab or Python is required as well a solid understanding of linear algebra.
You can find my report here:
