End-to-end machine learning for experimental physics: using simulated data to train a neural network for object detection in video microscopy

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.We demonstrate the power of this full-stack approach by applying it to the study of topological defect annihilation in systems of liquid crystal freely-suspended films. This specific experimental system requires accurate observations of both the spatial distribution of the defects and the total number of defects, making it an ideal system for testing the robustness of the trained network. The fully trained network was found to be comparable in accuracy to human hand-annotation, with four-orders of magnitude improvement in time efficiency. arXiv:1908.05271v1 [cond-mat.soft]

Learning physical properties of liquid crystals with deep convolutional neural networks

“…In fact, there are several basic and applied science scenarios that can benefit from these techniques, which goes far beyond the exclusive use in liquid crystals research. Upon correct training and design, neural networks and other machine learning methods have proved useful for identifying phase transitions 44,48 (thus coming in aid to regular thermal characterization such as differential scanning calorimetry measurements), pattern formation and pattern identification 49 (thus replacing the need for ever more specialized imaging tools and helping researchers to pick up very details). Other examples of success of machine learning methods include investigation of biological materials 50 , deep space investigation 51 , and the search for early stage breast cancer by looking for calcification cluster on mammograms 52 .…”

Characterising soft matter using machine learning

“…Existing review articles introduce machine learning 4,5 and cover topics such as drug discovery, 6 multiscale design, 7,8 active matter, 9 fluid mechanics, 10 and chemical engineering. 11 I have chosen a handful of example cases, hence unfortunately I miss a great deal of the existing literature, for example, on amyloid assembly, [12][13][14] analysis of image data, [15][16][17] density functional theory, 18,19 drying blood, 20 liquid crystals, [21][22][23][24][25][26] modeling differential equations [27][28][29] nanoparticle assembly, 30,31 network aging, 32 optimising microscopy, 33 polymers, [34][35][36][37][38][39][40][41] speeding up simulations 42,43 and 3d printing. [44][45][46] Machine learning has a reputation for being applied in haste with too little follow-up.…”

Deep semi‐supervised classification based in deep clustering and cross‐entropy

“…Classification, which is a supervised learning task, is relevant in the context of data mining and machine learning. It has many distinct applications for different areas, such as energy systems, biology, medicine, facial recognition, image processing, and object detection 1–6 …”