Photo by lil artsy/Pexels

Associations and Intelligence for AIs

Glue and substrate for learning and cognition

Keno Leon
7 min readOct 24, 2022


An academic course on AGI is probably decades away but when it is finally written I bet there will be a chapter devoted to associations which as we will see are the foundation of complex behavior be it artificial or biological, come along as we take a look and maybe make that first draft.

👋 Hi there 👋 all my content is free for Medium subscribers, if you are already a subscriber I just wanted to say thank you ! 🎉 If not and you are considering subscribing, you can use my membership referral link, you will be supporting this and other high quality content, Thank you ! ⭐️ Subscribe to Medium ! ⭐️

When two objects, qualities, classes, or attributes, viewed together by the mind, are seen under some connexion, that connexion is called a relation. Augustus De Morgan


Associations imply a relationship between things, that is as general a definition as we can get, if we look at biological associations, ie the process of forming mental connections or bonds between sensations, ideas, or memories we get closer to a working definition but as we are after artificial analogs we would also need to formalize things a bit more.

Relation. In Mathematics, associations start out as relations and have their own language which you might already know, a = b for instance means that a is related to b by means of being equal in some quality, (look also at finitary relationships),these are bedrock definitions but might be too fundamental for our needs.

While relations are our ground truth, graphs which can model pairwise relationships can be more useful, ( see also binary relations ), here for instance is a simple graph where a relationship of some kind exists between A and B :

And some more specific examples :