Menu

temporal forks... again...

2013-05-17
2013-05-17
  • Magnus Wootton

    Magnus Wootton - 2013-05-17

    So if a column isnt predicted, all cells become active. My system allocates synapses randomly to the data, so if I allocate all the synapses of the dendrite to one column then itll pretty much always be all cells active.

    I thought of a solution, per dendrite I only allocate once at a column no matter how many cells active, and that sorta sounds right.

    But the problem of forking still remains in my head.

     
  • Magnus Wootton

    Magnus Wootton - 2013-05-17

    i read another post, and yes this is indeed a problem we must think about. i will finish my implementation and put it here tho.

     

Log in to post a comment.

MongoDB Logo MongoDB