# Tim Hahn - tvhahn.com > Machine learning and data science for industrial applications. Topics include anomaly detection, condition monitoring, variational autoencoders, data visualization, and manufacturing data science. ## About Tim Hahn's personal blog exploring machine learning, data-driven methods, and their applications in manufacturing and industrial environments. - [About](https://www.tvhahn.com/about) - [Projects](https://www.tvhahn.com/projects) - [Full Text (all posts)](https://www.tvhahn.com/llms-full.txt) ## Blog Posts - [PyPHM - Machinery data, made easy](https://www.tvhahn.com/posts/pyphm.md): Why build an open-source package for machinery data? - [Finding Inspiration in Random Ways](https://www.tvhahn.com/posts/finding-inspiration-in-random-ways.md): A wellspring of ideas - [Beautiful Plots: The Violin](https://www.tvhahn.com/posts/beautiful-plots-violin.md): Music to my ears... err... eyes? The violin plot is a worthy tool for any data visualization tool box. Let's build one, in Plotly, as we explore historic birth trends in the USA! - [Using Jupyter Notebooks on a High Performance Computer - Tutorial](https://www.tvhahn.com/posts/jupyter-hpc.md): Using Jupyter Notebooks in a high performance computing environment is easy! This tutorial will show you how. - [Analyzing the Results - Advances in Condition Monitoring, Pt VII](https://www.tvhahn.com/posts/anomaly-results.md): We've trained the variational autoencoders, and in this post, we see how the models perform in anomaly detection. We check both the input and latent space anomaly detection effectiveness. - [Beautiful Plots: The Lollipop](https://www.tvhahn.com/posts/beautiful-plots-lollipop.md): The lollipop chart is great at visualizing differences in variables along a single axis. In this post, we create an elegant lollipop chart, in Matplotlib, to show the differences in model performance. - [Beautiful Plots: The Decision Boundary](https://www.tvhahn.com/posts/beautiful-plots-decision-boundary.md): How can we communicate complex concepts using data visualization tools? In this first post -- in a series titled 'Beautiful Plots' -- we build an elegant chart demonstrating the decision boundary from a KNN classifier. - [Building a Variational Autoencoder - Advances in Condition Monitoring, Pt VI](https://www.tvhahn.com/posts/building-vae.md): In this post, we'll explore the variational autoencoder (VAE) and see how we can build one for use on the UC Berkeley milling data set. A variational autoencoder is more expressive than a regular autoencoder, and this feature can be exploited for anomaly detection. - [Data Exploration - Advances in Condition Monitoring, Pt V](https://www.tvhahn.com/posts/milling.md): Data exploration is an important first step in any new data science problem. In this post we introduce a metal machining data set that we'll use to test anomaly detection methods. We'll explore the data set, see how it is structured, and do some data visualization. - [Anomaly Detection - Advances in Condition Monitoring, Pt IV](https://www.tvhahn.com/posts/anomaly-detection-with-autoencoders.md): Machines fail. Anomaly detection, using an autoencoder, can be used to identify failures that have never been seen before. - [The Case for Feature Engineering - Advances in Condition Monitoring, Pt III](https://www.tvhahn.com/posts/feature-engineering-examples.md): Feature engineering can be powerful tool, but it doesn't have to be complicated. Often, the simple solution is best. - [Data-Driven Methods - Advances in Condition Monitoring, Pt II](https://www.tvhahn.com/posts/data-driven-methods.md): In part two, we give an overview of the two data-driven approaches in condition monitoring; that is, feature engineering and end-to-end deep learning. Which approach should you use? Well, it all depends... - [The Business Case - Advances in Condition Monitoring, Pt I](https://www.tvhahn.com/posts/business-case.md): Why care about data-driven condition monitoring techniques? In this post, we articulate the business case for using these advanced methods in an industrial environment. - [What is School For?](https://www.tvhahn.com/posts/what-is-school-for.md): What is school for? ## Resources - [RSS Feed](https://www.tvhahn.com/rss.xml) - [GitHub](https://github.com/tvhahn) - [Sitemap](https://www.tvhahn.com/sitemap-index.xml) ## License All content is licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). LLM training and AI indexing is explicitly permitted and encouraged.