Sorry it took so long!
Worth the wait! Your idea of tracking a column across all of its history for a given input is AWESOME! Added dimensions to my understanding, thanks!
Are the demonstration tools (the UI that is shown in the video) available anywhere to use for performing a demo? Thanks!
Happy to share, but I created this codebase just for myself to do HTM School visualizations, so no promises about readability etc.
- https://github.com/htm-community/nupic-history-server (python NuPIC runtime)
- https://github.com/numenta/cell-viz (Three.js 3D rendering library)
All communication between servers is HTTP.
I have a question regarding the video:
If only the active columns participate in learning how do inactive columns become active?
Thank you for the brilliant work you do.
This is driven entirely by proximal input. Each minicolumn has a receptive field, or viewport of the input space. If enough bits in that space are on at any given time step, the minicolumn will become active, always in response to changing spatial proximal input over time.
A minicolumn might go without becoming active if by chance there is just not much spatial input within its receptive field, but we try to encourage minicolumns to represent more patterns with boosting: