add normalizePeak!

src/learn.jl

@@ -86,6 +86,9 @@ function learn!(kfn::kfn_1, correctAnswer::AbstractVector)
             nonFlipedSign = isequal.(n.subExInType, wSign)  # 1 not fliped, 0 fliped
             LinearAlgebra.normalize!(n.wRec, 1)
             n.wRec .*= nonFlipedSign  # set weight that fliped sign to 0 for random new connection
+            # normalize wRec peak to prevent input signal overwhelming neuron
+            normalizePeak!(n.wRec, 2)
+
 
             synapticConnStrength!(n)
             #TODO neuroplasticity

src/snn_utils.jl

@@ -4,7 +4,7 @@ using Flux.Optimise: apply!
 export calculate_α, calculate_ρ, calculate_k, timestep_forward!, init_neuron, no_negative!,
         precision, calculate_w_change!, store_knowledgefn_error!, interneurons_adjustment!, 
         reset_z_t!, resetLearningParams!, reset_learning_history_params!, reset_epsilonRec!,
-        reset_epsilonRecA!, synapticConnStrength!,
+        reset_epsilonRecA!, synapticConnStrength!, normalizePeak!,
         firing_rate_error!, firing_rate_regulator!, update_Bn!, cal_firing_reg!,
         neuroplasticity!, shakeup!, reset_learning_no_wchange!, adjust_internal_learning_rate!,
         gradient_withloss 
@@ -317,7 +317,18 @@ function neuroplasticity!(n::compute_neuron, firedNeurons::Vector)
     end
 end
 
-
+""" normalize a part of a vector centering at a vector's maximum value along with nearby value
+    within its radius. radius must be odd number
+"""
+function normalizePeak!(v::Vector, radius::Integer=2)
+    peak = findall(isequal.(n.wRec, maximum(n.wRec)))[1]
+    upindex = peak - radius
+    upindex = upindex < 1 ? 1 : upindex
+    downindex = peak + radius
+    downindex = downindex > length(v) ? length(v) : downindex
+    subvector = view(v, upindex:downindex)
+    normalize!(subvector, 1)
+end
 
 
 

src/types.jl

@@ -630,7 +630,7 @@ function init_neuron!(id::Int64, n::lif_neuron, n_params::Dict, kfnParams::Dict)
     n.synapticStrength = rand(-5:0.1:-3, length(n.subscriptionList))
 
     n.epsilonRec = zeros(length(n.subscriptionList))
-    n.wRec = LinearAlgebra.normalize!(rand(length(n.subscriptionList)), 1)
+    n.wRec = rand(length(n.subscriptionList))
     n.wRecChange = zeros(length(n.subscriptionList))
     n.alpha = calculate_α(n)
 end
@@ -649,7 +649,7 @@ function init_neuron!(id::Int64, n::alif_neuron, n_params::Dict,
     n.synapticStrength = rand(-5:0.1:-3, length(n.subscriptionList))
 
     n.epsilonRec = zeros(length(n.subscriptionList))
-    n.wRec = LinearAlgebra.normalize!(rand(length(n.subscriptionList)), 1)
+    n.wRec = rand(length(n.subscriptionList))
     n.wRecChange = zeros(length(n.subscriptionList))
 
     # the more time has passed from the last time neuron was activated, the more 
@@ -671,7 +671,7 @@ function init_neuron!(id::Int64, n::linear_neuron, n_params::Dict, kfnParams::Di
     n.synapticStrength = rand(-5:0.1:-3, length(n.subscriptionList))
 
     n.epsilonRec = zeros(length(n.subscriptionList))
-    n.wRec = LinearAlgebra.normalize!(rand(length(n.subscriptionList)), 1)
+    n.wRec = rand(length(n.subscriptionList))
     n.wRecChange = zeros(length(n.subscriptionList))
     n.alpha = calculate_k(n)
 end