Neuro-symbolic AI emerges as powerful new approach
Neuro-Symbolic AI: Combining Neural Networks And Symbolic AI But adding a small amount of white noise to the image (indiscernible to humans) causes the deep net to confidently misidentify it as a gibbon. We use symbols all the time to define things (cat, car, airplane, etc.) and people (teacher, police, salesperson). Symbols can represent abstract concepts (bank transaction) or things that don’t physically exist (web page, blog post, etc.). Symbols can be organized into hierarchies (a car is made of doors, windows, tires, seats, etc.). Neuro-symbolic lines of work include the use of knowledge graphs to improve zero-shot learning. Background knowledge can also be used to improve out-of-sample generalizability, or to ensure safety guarantees in neural control systems. Other work utilizes structured background knowledge for improving coherence and consistency in neural sequence models. Alternatively, in complex perception problems, the set of rules needed may be too large for the AI system to handle....