Summary of Beyond Development: Challenges in Deploying Machine Learning Models For Structural Engineering Applications, by Mohsen Zaker Esteghamati et al.
Beyond development: Challenges in deploying machine learning models for structural engineering applications
by Mohsen Zaker Esteghamati, Brennan Bean, Henry V. Burton, M.Z. Naser
First submitted to arxiv on: 18 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computational Engineering, Finance, and Science (cs.CE); Machine Learning (stat.ML)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper aims to address the challenges of deploying machine learning (ML) models in structural engineering by discussing two illustrative examples. The authors focus on common pitfalls such as model overfitting and underspecification, training data representativeness, variable omission bias, and cross-validation. To develop suitable ML models for real-world applications, rigorous validation techniques are crucial, including adaptive sampling, physics-informed feature selection, and considerations of model complexity and generalizability. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper explores how to make machine learning work in structural engineering. Currently, ML solutions are only tested as ideas and not used in real-life projects. The authors use two examples to show the problems that can happen when trying to develop ML models for real-world use. They discuss issues like model overfitting, bad training data, leaving out important information, and making sure the model is good enough to work on new data. |
Keywords
* Artificial intelligence * Feature selection * Machine learning * Overfitting
