Applied Machine Learning (Spring 2022)

The second version of the course I developed in fall of 2019 (see full description below) has now been co-listed as an upper division undergraduate course.

Microscopic Simulation Methods (MSE 991) (Fall 2021)

This is a modification of the graduate course I taught on particle-based simulation methods – see the full description below. This variant covered only two methods: Monte Carlo methods (Metropolis, SSA, tau-leap) and molecular dynamics.  Along the way, related background topics were covered: mechanics, statistical mechanics, thermodynamics, Markov chains and integrators. The course was 50/50 lecture/flipped, with in-class projects each week.

High Energy-Density Physics (Spring 2020)

This course is taught by University of Michigan by Prof. Kuranz and shared with MSU as a special topics course. I am the MSU faculty member for the course, but I act primarily as a local organizer and not an instructor. If you are interested in this course, contact me or Prof. Kuranz at University of Michigan.

Applied Machine Learning (Fall 2019)

This is a graduate level (CMSE 890) course that is project based with in-class group coding projects every week. A major component of the course is a capstone three-hour poster session of individual projects (typically connected with the PhD topic of the student) by each student.

Prerequisites

  • Computational modeling (see below)
  • Multivariable calculus
  • Advanced Python programming
  • Some experience with linear algebra, statistics and optimization

Topics

  • Scientific Python stack (NumPy, SciPy, Pandas, Seaborn, Matplotlib, Scikits)
  • Linear Algebra
  • Statistics
  • Optimization
  • Classifiers (decision trees, support vector machines, perceptrons, KNN)
  • Gaussian process regression
  • Neural networks (neural network zoo)
  • Dimensionality reduction (PCA, AE, LLE, MDS)
  • Tools of the trade: confusion matrices, pipelines, learning curves, hyperparameter optimization, visualization, cross validation, etc.
  • Complete Scikit-Learn ecosystem and introduction to Keras (TF 2.0)
  • History of machine learning

Textbook

Image result for hands on machine learning

Kinetic Theory (Fall 2018)

Prerequisites

Topics

Textbook

Image result for liboff kinetic theory

Particle-Based Simulation Methods (Spring 2018)

This is a graduate-level special topics course. Like most courses I have developed, this is a flipped classroom course with in-class group projects alternating with lectures/discussions. As with all special topics course, the content can be adpated to the needs of the students.

Prerequisites

  • Basic knowledge of physics (ideally the equivalent to an undergrad in physics)
  • Very strong programming skills in any language (many students use high-performance Python)

Topics

  • Molecular dynamics (MD)
  • Dissipative particle dynamics (DPD)
  • Particle in cell (PIC)
  • Smoothed-particle hydrodynamics (SPH)

Textbook

There is no textbook for this course, but I provide notes that are in the form of a textbook.

Computational Modeling (Spring 2017, Fall 2017, Spring 2020, Spring 2021)

Prerequisites

  • Calculus I

Topics

  • Python
  • data science
  • mathematical modeling

Textbook

  • none (all content is given in Jupyter notebooks)

Leave a Reply