Vortragende Person/Vortragende Personen:
Lukas Rauch

The abundance of text data and the emergence of powerful deep learning models have rapidly advanced Natural Language Processing (NLP). However, tailoring models to specific tasks still demands human-annotated data, which can be time-consuming. Active Learning strategically involves humans in the learning loop, selecting instances for annotation to maximize performance gains. This approach optimizes human effort and enhances the model’s adaptability, making training more efficient.

What to Expect:
In this full-day workshop, participants will delve into the fundamentals of Human-In-The-Loop Learning and (Deep) Active Learning. Through hands-on exercises, attendees will learn to design a (Deep) Active Learning Cycle using Python.

Requirements:

• Basic proficiency in Python
• Fundamental knowledge of Machine Learning/Deep Learning
• Bring your own laptop to fully engage in the workshop activities

Find more information and registration. For inquiries, please contact the following email address.