use LinearAlgebra.normalize!(vector, 1) to adjust weight after weight merge

src/Ironpen.jl

@@ -34,13 +34,8 @@ using .interface
 
 """ 
     Todo:
-        [*6] time-based learning method based on new error formula 
-            (use output vt compared to vth instead of late time)
-            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            
-        [7] use LinearAlgebra.normalize!(vector, 1) to adjust weight after weight merge         
+                   
+                
         [9] verify that model can complete learning cycle with no error
         [*5] synaptic connection strength concept. use sigmoid, turn connection offline
         [8] neuroplasticity() i.e. change connection
@@ -56,6 +51,13 @@ using .interface
             "inference"
         [DONE] output neuron connect to random multiple compute neurons and overall have 
             the same structure as lif
+            [DONE] time-based learning method based on new error formula 
+            (use output vt compared to vth instead of late time)
+            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 
+        [DONE] use LinearAlgebra.normalize!(vector, 1) to adjust weight after weight merge 
 
     Change from version:    v06_36a
         - 

src/learn.jl

@@ -162,6 +162,7 @@ function learn!(n::lif_neuron, error::Number)
  
     ΔwRecChange = n.eta * error
     n.wRecChange = (n.subExInType * n.wRecChange) + ΔwRecChange
+    LinearAlgebra.normalize!(n.wRecChange, 1)
 
     # check for fliped sign, 1 indicates non-fliped sign
     wSign = sign.(n.wRecChange)
@@ -182,6 +183,7 @@ function learn!(n::alif_neuron, error::Number)
 
     ΔwRecChange = n.eta * error
     n.wRecChange = (n.subExInType * n.wRecChange) + ΔwRecChange
+    LinearAlgebra.normalize!(n.wRecChange, 1)
 
     # check for fliped sign, 1 indicates non-fliped sign
     wSign = sign.(n.wRecChange)
@@ -198,6 +200,7 @@ function learn!(n::linear_neuron, error::Number)
  
     ΔwRecChange = n.eta * error
     n.wRecChange = (n.subExInType * n.wRecChange) + ΔwRecChange
+    LinearAlgebra.normalize!(n.wRecChange, 1)
 
     # check for fliped sign, 1 indicates non-fliped sign
     wSign = sign.(n.wRecChange)