Pre-Conference Course: An Introduction to Machine Learning and Data Science for Engineers

Standing on the Shoulders of Giants
Rosen Plaza Hotel, Orlando, FL  |  January 29–February 1, 2024

An Introduction to Machine Learning and Data Science for Engineers

Sunday, January 28, 2024 | 9:00 a.m. - 6:00 p.m.

Machine Learning (ML) and data science are having a huge impact on the way modern engineering is being approached. This is due to three important factors: an exponential increase in available data from in-service systems; significant theoretical developments and new algorithms; several programming frameworks which lower the barrier of entry to these new methods. However, engineering applications still pose unique and challenging use cases for ML tasks. This course will focus on the fundamentals of ML which will allow attendees to make informed decisions about the most appropriate ways to apply this new technology to their problems.

The course will be a mixture of example-based seminars and hands-on computer sessions.

1. What is Machine Learning (ML)?
  • ML with an engineering mindset
  • Fundamental tasks in ML
  • From engineering problems to ML solutions
    • Data exploration, preprocessing, etc.
2. Regression (materials tests, wind turbine examples)
  • Meaningful regression in engineering
  • Linear least squares
    • Not-so-linear bases
    • Controlling complexity and domain expertise
  • Maximum likelihood and Bayes's rule
    • A probability primer
    • Thinking generatively
    • Bayes Rule to encode engineering knowledge
  • Bayes Linear Regression
    • Conjugate Bayesian linear regression
    • Non-conjugate – discuss don’t derive
3. Classification (Acoustic emission example)
  • Why group data?
  • Feature selection and dimensionality reduction
    • PCA and others
  • What is similarity and how to measure it?
  • The K-nearest-neighbour algorithm
  • Gaussian Mixture models
  • Logistic regression (if we have time)
4. Clustering/Density Estimation (Acoustic emission example)
  • What if labels are unknown?
  • What is similarity and how to measure it?
  • The K-means algorithm for clustering
  • Gaussian Mixture Models for clustering
    • Distances link to probabilities
    • The EM method as an extension of K-means
5. Advanced Topics
  • Semi-parametric models and physics-informed ML
  • Semi-supervised approaches to clustering
  • Neural Networks and Deep Learning
  • Gaussian processes

Lawrence Bull

Lawrence is a research associate in the Engineering Dept. at the University of Cambridge, within the Computational Statistics and Machine Learning group. He researches statistical methods for monitoring telemetry data from systems and infrastructure, working closely with the Cambridge Centre for Smart Infrastructure and Construction (CSIC). Previously, he worked at the Alan Turing Institute in the Data-Centric Engineering programme and the Dynamics Research Group at the University of Sheffield.

The regular course fee is $500 and the student fee is $250. Course fee includes lunches, course handout material, and refreshment breaks. Lodging and additional food or materials are not included.

If the course is cancelled for any reason, the Society for Experimental Mechanics’ liability is limited to the return of the course fees.

Attendees are encouraged to bring their own laptops. None will be provided.