implement start learning

src/Ironpen.jl

@@ -34,13 +34,15 @@ using .interface
 
 """ 
     Todo:
-        [*3] implement "start learning", reset learning and "during_learning", "end_learning and
-            "inference"
-        [4] output neuron connect to random multiple compute neurons
-        [7] add time-based learning method. 
-            [] implement "thinking period"
+        [7] time-based learning method based on new error formula
+            if output neuron not activate when it should, use output neuron's 
+                (vth - vt)*100/vth as error 
+            if output neuron activates when it should NOT, use output neuron's
+                (vt*100)/vth as error                       
+        [*4] output neuron connect to random multiple compute neurons and have the same structure
+            as lif
         [8] verify that model can complete learning cycle with no error
-        [5] synaptic connection strength concept
+        [5] synaptic connection strength concept. use sigmoid
         [6] neuroplasticity() i.e. change connection
         [] using RL to control learning signal
         [] consider using Dates.now() instead of timestamp because time_stamp may overflow
@@ -50,6 +52,8 @@ using .interface
         [DONE] each knowledgeFn should have its own noise generater
         [DONE] where to put pseudo derivative (n.phi)
         [DONE] add excitatory, inhabitory to neuron
+        [DONE] implement "start learning", reset learning and "learning", "end_learning and
+            "inference"
 
     Change from version:    v06_36a
         -