University of Pennsylvania - Spring 2024
Instructor: Paris Perdikaris
This repository contains all course materials for ENM5310: Data-driven Modeling and Probabilistic Scientific Computing, a graduate-level machine learning course designed specifically for engineering students. The repository is updated weekly as we progress through the semester.
- Lecture Slides: Weekly presentation materials covering theoretical foundations and practical applications
- Lecture Notes: Supplementary notes and derivations for each topic
- Jupyter Notebooks: Interactive tutorials and computational exercises
- Assignment Solutions: Complete solutions released after submission deadlines
- Project Templates: Starter code and guidelines for the final project
- Supplementary Papers: Research articles and technical papers relevant to course topics
- Reference Materials: Additional resources for deeper understanding of concepts
This graduate-level course provides comprehensive coverage of machine learning techniques applied to engineering problems. Students gain both theoretical understanding and practical expertise through:
- Mathematical Foundations: Probabilistic modeling, Bayesian inference, optimization
- Modern Architectures: Deep learning, Transformers, neural operators
- Engineering Applications: Computational fluid dynamics, materials discovery, climate modeling
- Uncertainty Quantification: Physics-aware modeling and probabilistic approaches
- Linear Algebra (MATH 240/513 or ENM 240)
- Differential Equations (MATH 430, ENM 321, or ENM 503)
- Python programming proficiency
- Graduate standing or instructor permission
- Python: Anaconda distribution
- ML Libraries: JAX, PyTorch
- Cloud Computing: Google Colab for GPU/TPU access
ENM5310/
├── slides/ # Weekly lecture slides and materials
├── notebooks/ # Jupyter notebooks and tutorials
├── assignments/ # Homework problems and solutions
├── readings/ # Supplementary papers and materials
-
Clone the repository:
git clone https://github.com/[username]/ENM5310.git cd ENM5310 -
Set up Python environment:
conda create -n enm5310 python=3.9 conda activate enm5310 pip install -r requirements.txt
-
Launch Jupyter:
jupyter notebook
This repository is updated weekly with new content including:
- Lecture slides and notes
- Code examples developed in class
- Assignment materials and solutions
- Additional resources and readings
- Instructor: Paris Perdikaris
- Teaching Assistant: Shawn Koohy
- Course Website: https://www.seas.upenn.edu/~enm5310/
Students are encouraged to:
- Report issues or bugs in code examples
- Suggest improvements to documentation
- Share interesting applications or extensions
Course materials are provided for educational use by enrolled students. Please respect intellectual property rights and university policies regarding academic integrity.
This repository supports ENM5310: Data-driven Modeling and Probabilistic Scientific Computing at the University of Pennsylvania. Materials are updated regularly throughout the semester.