This digital lunch session will address the challenges of building complex AI systems when training data is scarce. Join Daniel Herman, PhD, and Stefan Remman from Chronos.ai as they share strategies to overcome this issue, emphasizing that solutions vary based on the specific use case. They will present real-world examples from their work in computer vision and AI, including subsea computer vision tasks.
Key insights from the webinar include: - Leveraging Model-Supported Annotation and existing metadata to generate training labels. - Transitioning from The Hybrid Approach of classical CV to The Flywheel Effect, demonstrating how to create models that autonomously seek their next lessons.
About the lunch webinars: These brief professional sessions are designed for easy participation during lunchtime, running from 11:30 to 12:00. The format includes approximately 20 minutes of presentation followed by 10 minutes for questions and answers.
Attendance is free.
