Hi all,

This new variant of recurrent NN (conceptor networks) looks interesting,

http://arxiv.org/abs/1403.3369

In fact it looks like a better-realized variant of the idea of "glocal
neural nets" that my colleagues and I experimented with a few years
ago,

http://www.sciencedirect.com/science/article/pii/S0925231210002808

The basic idea is to

-- create a recurrent NN

-- use PCA to classify the states of the NN

-- create explicit nodes or neurons corresponding to these states, and
then to imprint these states directly on the dynamics

So there is a loop of "recognizing patterns in the NN and then
incorporating these patterns explicitly in the NN dynamics", which is
a special case of the process of "a mind identifying patterns in
itself and then embodying those patterns explicitly in itself", which
I have conjectured to be critical to cognition in general (and which
underlies the OpenCog design on a philosophical level...)

There is some hacky Matlab code here implementing the idea,

http://minds.jacobs-university.de/sites/default/files/uploads/SW/ConceptorsTechrepMatlab.zip

but as code, it's pretty specialized to the exact experiments
described in the above technical report...

My intuition is that this sort of network would fit very well inside a
DeSTIN node, for a couple reasons

1)
It has demonstrated ability to infer complex dynamical patterns in time series

2)
It explicitly creates "concept nodes" representing the patterns
recognized, which could then be cleanly exported into a symbolic
system like OpenCog

...

So, this is a pretty nice combination.

Of course, conceptor networks are still at the research stage, so
getting them to really work inside DeSTIN nodes would require a
significant amount of fiddling...

But it's cool stuff ;)

-- Ben


-- 
Ben Goertzel, PhD
http://goertzel.org

"In an insane world, the sane man must appear to be insane". -- Capt.
James T. Kirk

"Emancipate yourself from mental slavery / None but ourselves can free
our minds" -- Robert Nesta Marley


-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657
Powered by Listbox: http://www.listbox.com

Reply via email to