I have been thinking, one of the current challenges in building Artificial General Intelligence (AGI) right now is actually getting it to understand Context. And for it to understand Context, a knowledge base is a must, in my opinion. And I have shared in another post about a knowledge graph to achieve it.
Over in this post, I'm going to briefly lay out the areas that we need to focus on when we are building a knowledge base, regardless of the architecture/structure of it. Here they are:
Recognition
It is the stage where the knowledge base comes across some unknown knowledge, study through the knowledge and recognize what it should build into itself.
For instance, a knowledge graph may recognize what and how to store a new piece of knowledge, what should be its entities and edges and what dimension to store it.
Storage
Storage as the names says is storing it namely the data schema, that is after recognition rather because Recognition has a lot more focus on the shall and what, while Storage will focus on the How, what should store at the Edges and Entity/Nodes but also keeping in mind Retrieval, which is next.
Retrieval
Retrieval focuses on which part of the knowledge base to retrieve, what to retrieve and also the speed of retrieval as well.
Learning
It is a process build across the area so that the knowledge base, like a human, can improve in all the areas, and moreover, knowledge evolves thus we need to allow the knowledge base to get better at it and thus Learning is a must.
These are some thoughts at the moment and hoping to develop it further with a good friend of mine. :)
So...what are your thoughts? Will love to hear from you! You can share them with me on my LinkedIn. Please feel free to link up on LinkedIn or Twitter (@PSkoo). Do consider signing up for my newsletter too.
Thanks for spending your time on reading this. Greatly appreciated! :)