# End-to-End Machine Learning for Experimental Physics: Using Simulated Data to Train a Neural Network for Object Detection in Video Microscopy

## TL;DR

This paper presents a method to train neural networks for object detection in microscopy videos using simulated data generated dynamically, reducing the need for extensive real-world training datasets.

## Contribution

It introduces a full-stack computational approach that creates realistic simulated training data on-the-fly for experimental physics applications.

## Key findings

- Neural networks trained on simulated data perform well on real experimental data.
- The on-the-fly data generation reduces the time and effort needed for training data collection.
- The method enables effective object detection in microscopy videos with minimal real-world data.

## Abstract

We demonstrate a method for training a convolutional neural network with simulated images for usage on real-world experimental data. Modern machine learning methods require large, robust training data sets to generate accurate predictions. Generating these large training sets requires a significant up-front time investment that is often impractical for small-scale applications. Here we demonstrate a `full-stack' computational solution, where the training data set is generated on-the-fly using a noise injection process to produce simulated data characteristic of the experimental system.