Introduction Want to track how much you spend on what but don’t want to download every supermarket’s app / manually fill some sort of spreadsheet? The app ( github) described here can be hosted on your machine or online so you can take a picture of your receipt with your phone upload it and later download the extracted data using a desktop machine. App Overview If you have a receipt like ...
Let’s continue our quest, started in the previous post, to classify individual atoms based on their surroundings. If atomistic simulations are foreign to you I recommend checking out this wiki article to get an idea of what I am talking about. This post is probably a bit atomistic simulationy technical, but don’t worry if not all aspect become perfectly clear. The main message is that that for crystals one can use machine learning to discover useful classes without the need for painstaking prior labelling. The rest of this post just goes a bit more into detail of the required bits of machinery to achieve this discovery of classes. ...
In this blog post I will show you how freely available machine learning tools ( scikit-learn and tensorflow) in Python can be used to solve a non-trivial task, the classification of individual atoms in some complex arrangement of atoms. The jupyter notebook used here can be found at the end of this post. The aim of this blog post is to give you an insight in how classifiers for atoms can be created and tested and to enable you to create and test your own, using a selection of types of crystals of interest to you. ...