On November 15th, join us at RocketSpace London for our AI workshop. We are bringing together top software engineers within the AI community to present their frameworks and research projects.

At this workshop, Miroslav Batchkarov from Skim Technologies and Ling Zhang from Aiden.ai will present two frameworks they've built: PyOrbital and Fuzzy Search.

Workshop 1: Model distribution with PyOrbital (Miroslav Batchkarov)

Skim Technologies develops machine learning models to extract information from web pages, one of the most accurate content extractors on the market served via their API. One of the problems they faced in production is how to move large models between servers while keeping them private. Since no existing tool met all of the requirements, they made their own and open-sourced it.

Workshop 2: Building a fast fuzzy searcher and spell checker (Ling Zhang)

Spelling is hard, really hard. It's an everyday user frustration to try to search for a friend's name or the name of a restaurant that they heard but end up writing it wrong. In this talk, he will cover a python implementation of a single fast algorithm that can recover from spelling errors, typing errors, and even transliteration mistakes! He will also integrate this with a language model to make it context aware. With this technique, you can build powerful fuzzy text searchers and spell checkers. Fast fuzzy search can be used to boost the accuracy of existing tools like indexed DB searches, elastic search, NLP, and speech recognition.