article
September 18, 2023
4 min read
0 views
Time-Series Anomaly Detection With an Autoencoder: From Paper to Production
An LSTM autoencoder trained on normal sensor readings detects anomalies by reconstruction error. The threshold selection, false-positive rate, and retraining cadence matter more than the architecture.
An LSTM autoencoder trained on normal sensor readings detects anomalies by reconstruction error. The threshold selection, false-positive rate, and retraining cadence matter more than the architecture.
Overview
This note is part of the field-notes archive generated for this site. The summary below is the published excerpt; you can expand the full write-up anytime in the CMS.
Related notes
Tags
- anomaly-detection
- time-series
- autoencoder
- machine-learning
- iot
M
Manish Bookreader
Electronics enthusiast, Embedded Systems Expert, Linux/Networking programmer, and Software Engineer passionate about AI, electronics, books, and cooking.
