update TODO

src/Ironpen.jl

@@ -37,9 +37,10 @@ using .interface
         [1] implement connection strength based on right or wrong answer
         [2] during 0 training if 1-9 output neuron fires, adjust weight only those neurons
         [3] implement dormant connection
+        [4] Δweight * connection strength 
         [] using RL to control learning signal
         [] consider using Dates.now() instead of timestamp because time_stamp may overflow
-        [4] training should include adjusting α, neuron membrane potential decay factor
+        [5] training should include adjusting α, neuron membrane potential decay factor
             which defined by neuron.tau_m formula in type.jl
 
         [DONE] each knowledgeFn should have its own noise generater