Author(s): Maxwell’s Demon

Originally published on Towards AI.

Optimally combining prior knowledge with new data

Let’s start with an example. Say a lab technician knows from long-term experience that the lab’s temperature usually hovers around 20 °C. On a particular day, she notices some changes in the environment and decides to measure it. The thermometer, however, is noisy — it can be off by about ±2 °C. She cannot fully trust her prior knowledge, nor can she rely entirely on the new measurement.

This article discusses the concept of linear estimators by using a practical example to illustrate how a lab technician should optimally combine her previous knowledge of ambient temperature with noisy measurements. It emphasizes the theoretical basis for linear estimators, providing a simplified mathematical treatment, and explores their relevance in everyday scenarios, pointing out how the method reflects concepts in Bayesian thinking and can be applied in various contexts such as machine learning and system identification.

Read the full blog for free on Medium.

Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.

Published via Towards AI