Deep learning methods have had tremendous success in a wide variety of applications including self driving, infrastructure inspections, design optimization, robotic navigation, and even in solving differential equations! What is incredible is that the deep learning solutions in all these applications stem from a few, dare I say, simple ideas. This course is aimed at providing a hands-on introduction to deep learning for engineers together with domain specific examples. Topics that will be covered include
- Linear classifiers
- Multi-layer neural networks
- Convolutional neural networks
- Recurrent neural networks
- Generative networks
- Physics-informed deep learning
- Reinforcement learning
Coursework includes programming assignments in Python,
quizzes and a final project.
Instructor: Vedhus Hoskere (vhoskere -at- central.uh.edu)
Prerequisites: Multi-variable calculus, linear algebra, programming in python. No previous exposure to machine learning is required.
Reference material:
- Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, 2016.
- J. Nathan Kutz and Steven L. Brunton, Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control
- Intro to Deep Learning, University of Illinois, Fall 2018