Neuro-symbolic approaches in artificial intelligence National Science Review
Finally, their operation is largely opaque to humans, rendering them unsuitable for domains in which verifiability is important. In this paper, we propose an end-to-end reinforcement learning architecture comprising a neural back end and a symbolic front end with the potential to overcome each of these shortcomings. As proof-of-concept, we present a preliminary implementation of the architecture and apply it to several variants of a simple video game.
Everything you wanted to know about AI – but were afraid to ask – The Guardian
Everything you wanted to know about AI – but were afraid to ask.
Posted: Fri, 24 Feb 2023 22:00:00 GMT [source]