Neuro-Symbolic AI by Alexiei Dingli & David Farrugia

Author:Alexiei Dingli & David Farrugia
Language: eng
Format: epub
Publisher: Packt
Published: 2023-11-15T00:00:00+00:00

The idea behind NSAI

Bridging the intelligence gap between man and machine is our destination—the holy grail. The challenge of solving the physical brain’s complexity has intrigued researchers for years. Over the years, we raised and answered numerous questions; nonetheless, one question still prevails. Scientists know that we cannot understand the brain’s function to its entirety, especially its ability to develop common-sense knowledge—which essentially boils down to multiple complex associations that the brain can extract.

Defining common-sense knowledge

Common-sense knowledge is any knowledge that becomes almost second nature or apparent to us. For example, if we see a chair, we can practically assume we can sit on it. If we see a bed, we know that we can lie on it without falling through the mattress. The director of the MIT-IBM Watson AI Lab, David Cox, defines common-sense knowledge as “all of the implicit knowledge that we have that is never written down anywhere.”

Solving the issue of having machines not just learn common sense but also fully understand it (and its underlying knowledge) seems to be the next step for the new generation of AI techniques. Machine-enabled knowledge understanding is the objective.

How can we ever model something that we do not fully understand?

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.