> 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
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 )
no subject
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 )