Articles tagged with Evolutionary Robotics
Current AI systems lack internal embodiment, a property that humans take for granted, which can lead to performance and behavior limitations. Researchers propose a dual-embodiment framework to guide future research in building safer and more aligned AI models.
Researchers created a computational model that combines physiological signals, sensory input, and word information to construct human emotions. The model achieved an agreement rate of about 75% when compared to participants' self-reported emotional evaluations.
Researchers used an AI-assisted application to help people write cartoon captions for The New Yorker Cartoon Caption Contest. The tool analyzed incongruity and generated suggestions, resulting in jokes rated 30% funnier than those written without assistance.
A study by Universitat Rovira i Virgili's SeesLab research group shows machine learning algorithms may not always find interpretable models from data due to fundamental limitations. The importance of noise in data is highlighted, making it impossible to discover the correct model when variability is high.