Mechanical & Industrial Engrg 690D - Deep Learning/Engineering Appl

This course provides an in-depth exploration of deep learning techniques and their practical applications across various engineering applications. Topics include Feed Forward Neural Networks, Convolutional Neural Networks, Recurrent Neural Networks, Autoencoders, and Transformers applied to engineering applications such as demand forecasting; route optimization or transportation and delivery; inventory management; dimensionality reduction; anomaly detection in manufacturing and quality control; digital twin modeling; and surrogate of simulation models. Additionally, the course delves into the growing field of Interpretable Machine Learning, ensuring that students learn to not only create powerful models but also focus on techniques for interpretability and explainability. These skills are relevant for the safety critical applications that are typical in engineering, and to make models more transparent and understandable to stakeholders to enhance model deployment. Assignments will include computational problems for hands-on practical experience using established Python libraries and problem analyses, and methodological components that require a deeper understanding of mathematical concepts.

Open to graduate students in the College of Engineering. Students should have background in Python, linear algebra, probability & statistics, and statistical machine learning. If you have questions regarding eligibility, please contact the instructor.