http://anhinga-anhinga.livejournal.com/ ([identity profile] anhinga-anhinga.livejournal.com) wrote in [personal profile] anhinga_anhinga 2017-01-03 03:35 pm (UTC)

> The "computation matrix" *is* that prefix tree of chains of keys that we were talking about (aka recurrent map), and a rule for computing the next step is to traverse it up to each individual neuron and apply the neuron's function to the subtree of arguments, producing a new subtree of output values

Yes, this is an "up movement" of the two-stroke engine. In the current version of

https://github.com/jsa-aerial/DMM/blob/master/src/dmm/core.clj

see the comments starting from line 303 at the end of this file, and the two functions at the bottom implement the traversal (when you decide you want to read the code, the important function to understand is reduce, this whole DMM codebase is constructed around it: https://clojuredocs.org/clojure.core/reduce )

Post a comment in response:

This account has disabled anonymous posting.
If you don't have an account you can create one now.
HTML doesn't work in the subject.
More info about formatting