Since their introduction in 2017, transformer networks have become the go-to models for AI on text, boosting various applications from search over information extraction to AI-supported software development. This talk will introduce the technical foundations behind the hype from a deep learning practitioner’s perspective, including
* the fundamental concept behind transformers (multi-head attention)
* common architectures (such as BERT or the GPT series)
* deep learning practice and tooling.
Adrian Ulges is a professor with RheinMain University of Applied Sciences in Wiesbaden and an alumnus of TU Kaiserslautern (2009 PhD in computer science, 2005 diploma in computer science). He has been as a researcher with the German Research Center for Artificial Intelligence (DFKI) in Kaiserslautern (2005-2012), and has worked with Google as an intern (2005, Mountain View) and as a visiting scientist (2011, Zurich). His research focuses on machine learning and AI for text, and has…
Create Content Fast with AI: read more about Frase
Artificial intelligence makes it fast & easy to create content for your blog, social media, website, and more! Jasper is the AI Content Platform that helps you and your team break through creative blocks to create amazing, original content 10X faster.