1
$\begingroup$

I have just started reading about the SPA (semantic pointer architecture) and wondering how it relates to deep learning concepts.

$\endgroup$
  • 1
    $\begingroup$ There is not a lot in your question to go on in order to answer your question. What do you know about SPA? What do you know about deep learning concepts? What is it you have read? What (if anything) is confusing you or hard to understand? If you have only just started to read about SPA and there is nothing confusing or hard to understand, maybe you just need to read more to fully understand it in order to answer your own question. $\endgroup$ – Chris Rogers Apr 5 '18 at 10:03
  • 1
    $\begingroup$ Sorry @Chris, I'm the one who directed them to this site. I have should have given them more direction. erdal.karaca it would be helpful if you elaborated on your current understanding of each concept. $\endgroup$ – Seanny123 Apr 5 '18 at 17:39
2
$\begingroup$

Deep Learning (which is now supposed to be called Differentiable Programming?) is a means of doing inference over a set of data.

SPA is a Vector Symbolic Architecture (VSA) implemented using Holographic Reduced Representations (HRR). That is to say, sparse vectors represent symbols and there is a set of operations that can be used to combine them.

Consequently, SPA can be used as a sort of prior for Deep Learning to provide constraints on the representation it's learning.

For example, SPA could be used to represent the output of a visual system, which would then be used by other symbolic systems. In the case of Spaun, Deep Learning is used in the vision system to map images onto known symbols. These known symbols can then be manipulated in ways that would be impossible for Deep Learning to perform. For example, Rapid Variable Creation used for solving Raven's Progressive Matrices is impossible for Deep Learning to perform without any structural priors.

$\endgroup$

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.