Building and sharing machine learning demo applications: a practical tutorial

Registration required

It is becoming increasingly popular to share machine learning models with the community as web applications with an easy-to-use interface. Users can then adjust parameters or submit their own input and see the predictions generated by the underlying model. This tutorial is aimed at KTH researchers (all career levels welcome) who work with machine learning models but do not have the skills to build interactive applications for web. During the tutorial we will start from a trained model and demonstrate step by step how you can create a graphical user interface for your application, prepare it for deployment, and make it available on the web with a URL. We will demonstrate the use of specific tools which make this process easy and doable in under an hour, specifically we will demonstrate and try out Gradio  for app building. We will also demonstrate SciLifeLab Serve, a platform for hosting models and applications available to all researchers in Sweden.

The tutorial lasts 2 hours, with a break in the middle. After the tutorial all participants are invited for lunch. During the lunch participants will have an opportunity to informally chat with KTH Library staff and SciLifeLab Data Centre to discuss the needs for services and research infrastructure in research using machine learning methods.

This tutorial is open to everyone at KTH. The event is organised by the KTH Library in collaboration with SciLifeLab Data Centre.

We have room to accept 35 participants, on the first come first served basis. Those registered after that will be placed on the waiting list and offered a spot when someone cancels.

With any questions, feel free to contact serve@scilifelab.se .