Engineering Application of Deep Learning

(3 Credits)

Deep learning techniques are increasingly integral for prediction and estimation in a wide variety of engineering disciplines. We focus on the practice of deep learning, teaching students to efficiently train neural networks from basic feedforward networks to transformers and finetuning of foundation models. The course will cover introductory machine learning, feedforward MLPs, recurrent neural networks, convolutional networks, transformers, diffusion models, a brief overview of foundation model finetuning, and computational considerations such as memory and efficiency of models The course will emphasize the application of these techniques to a wide range of engineering tasks such as travel time prediction, satellite imagery classification, and video analysis. | Prerequisite: Knowledge of Python and Multivariable, Anti-requisite: CS-GY 6953 and ECE-GY 7123