Deploying Transformers & Building a Semantic Search Engine
Thanks to ML6 for virtually hosting us tonight! For those who would like to attend in person, please have a look at https://www.meetup.com/ai-campus-berlin/events/287901155/
Title: Vertex AI Pipelines for training and deploying Huggingface transformers.
Speaker: Maximilian Gartz
This talk touches upon three major developments in contemporary Machine Learning: First, transformers are gaining in popularity, with their applicability extending also to CV tasks. Second, machine learning pipelines that ensure robust and reproducible results become increasingly popular. Every cloud provider has their own toolbox for facilitating the implementation of such pipelines. Lastly, various frameworks try to resolve the problem of how to deploy trained models in a robust and scalable manner. This talk shows how to make use of these developments to implement an easily adaptable end-to-end Vertex AI Pipeline for training Huggingface Transformers models and deploying them with NVIDIAs Triton Inference Server.
Maximilian is an ML Engineer at ML6. His main interest lies in MLOps and particularly in end-to-end machine learning pipelines. At ML6 he was leading the first dive into Vertex AI Pipelines right after their release, which led to a wide adoption across projects. He has a strong focus on standardization and thus worked a lot on developing and deploying standard ML pipelines for different ML tasks.
Title: Where my docs at? A short story about building a semantic search engine.
Speaker: Matthias Richter
Lexical based information retrieval systems are great for quickly fetching relevant information in a large text corpus. Traditional systems search for exact matches of words and are not able to recognize synonyms or distinguish between ambiguous words. To tackle these challenges we can train a neural network that is able to understand the semantics of documents. Such networks could help us to find similar documents to a given query. We will give a brief overview about the main concepts on semantic search and concrete steps on how to build your own. Join us on the journey back to the relevant information in your document jungle.
Matthias is an ML Engineer at ML6 and is highly interested in a wide range of machine learning technologies. He mainly focuses on recent research in NLP and the practical usage of these approaches. Besides his work at ML6 he is passionate about endurance sports and up for any kind of adventure.