Adapting Like Humans: Embodied AI Beyond Datasets and Domains
Offered By: GAIA via YouTube
Course Description
Overview
Explore the cutting-edge developments in embodied AI systems through this 25-minute conference talk by Pier Luigi Dovesi, Senior AI Engineer at Silo AI. Delve into the evolution from traditional AI training methods to dynamic, adaptable systems that mirror human learning capabilities. Discover how real-time adaptation methodologies serve as crucial stepping stones towards embodied AI, enhancing robustness and applicability in real-world scenarios. Learn about the importance of AI embodiment in perceiving, interacting, and evolving with the environment. Gain insights into the practical applications of this research, including its use by Rain AI in neuromorphic computing. Follow the journey through superhuman perception, unsupervised AI, online domain adaptation, and real-time adaptation, concluding with future prospects and a Q&A session.
Syllabus
Introduction
Superhuman Perception
Unsupervised AI
Online Domain Adaptation
Hard Domain Adaptation
Realtime Adaptation
Example
Whats next
Questions
Taught by
GAIA
Related Courses
Introduction to Deep LearningMassachusetts Institute of Technology via YouTube Taming Dataset Bias via Domain Adaptation
Alexander Amini via YouTube Making Our Models Robust to Changing Visual Environments
Andreas Geiger via YouTube Learning Compact Representation with Less Labeled Data from Sensors
tinyML via YouTube Geo-localization Framework for Real-world Scenarios - Defense Presentation
University of Central Florida via YouTube