1
$\begingroup$

I was reading this paper by Neil Taatgen on primitive information processing elements (PRIMs), as a type of machine-language for ACT-R. In the paper he claims:

The absence of variables means that the binding problem is no longer an issue

From what I understand, the binding problem is about how variables are represented neurologically. Namely how they can be combined and retrieved, which has typically been a problem for most Connectionist architectures.

Why does the lack of variables in PRIMs (they seem to be just operations) mean that the binding problem is no longer an issue?

$\endgroup$
1
$\begingroup$

PRIMs doesn't claim to solve to binding problem. It just passes on the responsibility of representing the symbols and combining them accordingly. In this way the binding problem "is no longer an issue" of PRIMs, however it is a problem of whatever representational system it's working on top of. Whether it be symbolic like ACT-R or more neural, such as the NEF.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.