search

htm-community / comportex

Hierarchical Temporal Memory in Clojure
154 stars 27 forks source link

Decomplect layer-activate #37

Closed floybix closed 8 years ago

floybix commented 8 years ago

Separated cell activation from winner cell selection. And cell activation from temporal pooling logic.

A new (obvious?) axiom for the design: selecting winner cells should happen in the learn phase.

Think of the learn phase as on a slower time scale than the activate phase; only in the latter phase do sub-connected (weakly-connected?) synapses have any effect.

Now the selection of winner cells and segments is centralised into one place.

Pulled out the learning-related state into a new :learn-state record.

Started a CHANGELOG.md

mrcslws commented 8 years ago

I like how the meat of every function (its let vector) fits on the screen all at once. It's way easier to hold in my head when I can look at it without scrolling.

(Still reading)

floybix commented 8 years ago

Ha, you're right. Deleted now.

The whole TP mechanism is still up in the air afaik. Currently I have the stable bits input (from predicted source cells) used only for a single threshold comparison, to decide whether a layer is "engaged".

mrcslws commented 8 years ago

Looks good. Really nice cleanup. :+1: