Introduction to Scientific Machine Learning
This course introduces data science to engineers with no prior knowledge. Throughout the course, the instructor follows a probabilistic perspective that highlights the first principles behind the presented methods with the ultimate goal of teaching the student how to create and fit their own models.
ME53900
Credit Hours:
3Learning Objective:
- Represent uncertainty in parameters in engineering or scientific models using probability theory
- Propagate uncertainty through physical models to quantify the induced uncertainty in quantities of interest
- Solve basic supervised learning tasks, such as: regression, classification, and filtering
- Solve basic unsupervised learning tasks, such as: clustering, dimensionality reduction, and density estimation
- Create new models that encode physical information and other causal assumptions
- Calibrate arbitrary models using data
- Apply various Python coding skills
- Load and visualize data sets in Jupyter notebooks
- Visualize uncertainty in Jupyter notebooks
- Recognize basic Python software (e.g., Pandas, numpy, scipy, scikit-learn) and advanced Python software (e.g., pymc3, pytorch, pyro, Tensorflow) commonly used in data analytics.
Description:
This course introduces data science to engineers with no prior knowledge. Throughout the course, the instructor follows a probabilistic perspective that highlights the first principles behind the presented methods with the ultimate goal of teaching the student how to create and fit their own models.
Topics Covered:
The course starts with an extensive review of probability theory as the language of uncertainty, discusses Monte Carlo sampling for uncertainty propagation, covers the basics of supervised (Bayesian generalized linear regression, logistic regression, Gaussian processes, deep neural networks, convolutional neural networks), unsupervised learning (k-means clustering, principal component analysis, Gaussian mixtures) and state space models (Kalman filters). The course also reviews the state-of-the-art in physics-informed deep learning and ends with a discussion of automated Bayesian inference using probabilistic programming (Markov chain Monte Carlo, sequential Monte Carlo, and variational inference).Prerequisites:
- Working knowledge of multivariate calculus and basic linear algebra
- Basic Python knowledge
- Knowledge of probability and numerical methods would be helpful, but not required
Applied / Theory:
50 / 50Textbooks:
Computer Requirements:
Jupyter Notebook Jupyter notebooks are interactive documents that can simultaneously contain text, mathematics, images, and executable code. The executable code can be in many programming languages (e.g., R, Matlab), but we are only going to use Python in this course. The course uses Jupyter notebooks for the following content: Reading Activities, Hands-on Activities, and Homework Assignments. The rationale behind this choice is that it allows the student to focus on the mathematical methods rather than the programming and it ensures the reproducibility of the course content. Of course, understanding the code in Jupyter notebooks does require knowledge of Python, albeit it does not require knowing how to structure and call Python code from the command line. Jupyter notebooks can be run either on the students' personal computers (instructions vary with operating system and can be found here) or in several cloud computing resources. The recommended method for this class is to use Google Colab which is available free of charge and requires only a standard Google account. The activity links included in the course will take you automatically to a copy of the latest version of the corresponding Jupyter notebook which you can then save and edit on your Google Drive. If you do not want to create a Google account, then it is also possible to run the notebooks at Purdue's Jupyter Hub using your Purdue Career Account. This method requires more expertise and you may encounter several issues. When this occurs, please post a question on Piazza and the TA will help you out.
Access to the Jupyter Notebooks Repository As stated earlier, the recommended method for using the Jupyter notebooks of this class is to use Google Colab. The links to all the activities will take you directly to a Google Colab copy of the Jupyter notebook. If you want to use any alternative method (e.g., your personal computers Purdue's Jupyter Hub, or anything else), you will need access to the Jupyter Notebook repository for the class. Here you can find the Jupyter notebooks GitHub repository.